You searched for subject:(Prediction theory).
Showing records 1 – 30 of
225 total matches.
◁ [1] [2] [3] [4] [5] [6] [7] [8] ▶
Oregon State University
1.
Lejeune, Michel, 1944-.
A maximum likelihood approach to prediction with applications to binomial and Poisson populations.
Degree: PhD, Statistics, 1974, Oregon State University
URL: http://hdl.handle.net/1957/44148 
► Given a sample from a population whose distribution belongs to a parametric family we would like to make predictions on the outcome of a statistic…
(more)
▼ Given a sample from a population whose distribution belongs to a
parametric family we would like to make predictions on the outcome of
a statistic (generally the sample sum) of a future sample from the same
population. These predictions can be in the form of intervals with some
associated level of confidence or in the form of predictive distributions.
A "Maximum Likelihood Predictive Distribution" is introduced which
is easily accessible in most regular cases and under conditions similar
to those for the consistency of the maximum likelihood estimator converges
almost surely to the true distribution of the predicted variable
when the observed sample size becomes large.
The new approach is compared to frequentist and Bayesian approaches
and to another likelihood approach introduced by R. A. Fisher. The comparisons
are conducted for simple random sampling from Poisson populations
and from binomial populations. The various approaches yield quite similar results for all sample
sizes and tend to be equivalent to the method using normal approximations
when both the observed and future sample sizes tend to infinity such
that their ratio remains constant.
It is shown that the Maximum Likelihood Predictive Distribution is
almost identical to the Bayesian predictive distribution under prior
√λ in the Poisson case and prior √p(1 - p) in the binomial case.
These approaches are also considered for Poisson and binomial
stratified random sampling and the results compared.
Advisors/Committee Members: Faulkenberry, G. David (advisor).
Subjects/Keywords: Prediction theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Lejeune, Michel, 1. (1974). A maximum likelihood approach to prediction with applications to binomial and Poisson populations. (Doctoral Dissertation). Oregon State University. Retrieved from http://hdl.handle.net/1957/44148
Chicago Manual of Style (16th Edition):
Lejeune, Michel, 1944-. “A maximum likelihood approach to prediction with applications to binomial and Poisson populations.” 1974. Doctoral Dissertation, Oregon State University. Accessed January 23, 2021.
http://hdl.handle.net/1957/44148.
MLA Handbook (7th Edition):
Lejeune, Michel, 1944-. “A maximum likelihood approach to prediction with applications to binomial and Poisson populations.” 1974. Web. 23 Jan 2021.
Vancouver:
Lejeune, Michel 1. A maximum likelihood approach to prediction with applications to binomial and Poisson populations. [Internet] [Doctoral dissertation]. Oregon State University; 1974. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/1957/44148.
Council of Science Editors:
Lejeune, Michel 1. A maximum likelihood approach to prediction with applications to binomial and Poisson populations. [Doctoral Dissertation]. Oregon State University; 1974. Available from: http://hdl.handle.net/1957/44148
Oregon State University
2.
Olsen, Dale Edward.
Statistical prediction intervals.
Degree: PhD, Statistics, 1973, Oregon State University
URL: http://hdl.handle.net/1957/44403
► In many statistical applications an interval is needed that will contain the values of all J future observations with some preassigned probability. For example, suppose…
(more)
▼ In many statistical applications an interval is needed that will contain the values of all J future observations with some preassigned probability. For example, suppose twenty rockets have been fired in a test program and three have failed. If two more test programs are to be conducted, an interval that will, with probability 1-α, contain the maximum number of failures in either of the two programs is called an a confidence level
prediction interval. In this thesis a general procedure is given for predicting future observations when there is one unknown parameter and other conditions are satisfied. The normal and the gamma distributions are used as examples to illustrate the procedure in the continuous case. It is shown that Poisson random variables can be predicted using the negative multinomial distribution. Tables of negative multinomial probabilities are provided and approximation procedures are suggested. It is also shown that negative binomial random variables can be predicted using the multivariate beta negative binomial and binomial random variables can be predicted using the multivariate negative hypergeometric distribution. The
prediction intervals given in this thesis can also be used for simultaneous hypothesis testing for the Poisson, negative binomial and binomial distributions.
Advisors/Committee Members: Faulkenberry, G. David (advisor).
Subjects/Keywords: Prediction theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Olsen, D. E. (1973). Statistical prediction intervals. (Doctoral Dissertation). Oregon State University. Retrieved from http://hdl.handle.net/1957/44403
Chicago Manual of Style (16th Edition):
Olsen, Dale Edward. “Statistical prediction intervals.” 1973. Doctoral Dissertation, Oregon State University. Accessed January 23, 2021.
http://hdl.handle.net/1957/44403.
MLA Handbook (7th Edition):
Olsen, Dale Edward. “Statistical prediction intervals.” 1973. Web. 23 Jan 2021.
Vancouver:
Olsen DE. Statistical prediction intervals. [Internet] [Doctoral dissertation]. Oregon State University; 1973. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/1957/44403.
Council of Science Editors:
Olsen DE. Statistical prediction intervals. [Doctoral Dissertation]. Oregon State University; 1973. Available from: http://hdl.handle.net/1957/44403
Rutgers University
3.
Sharber, Justin, 1983-.
The predictive focus account of the principle of simplicity.
Degree: PhD, Philosophy, 2014, Rutgers University
URL: https://rucore.libraries.rutgers.edu/rutgers-lib/45460/
► This dissertation presents an account of the Principle of Simplicity, a prominent idea in the philosophy of science. The principle states that when a simple…
(more)
▼ This dissertation presents an account of the Principle of Simplicity, a prominent idea in the philosophy of science. The principle states that when a simple model and a complex model both predict the data, and all else is equal, the data supports the simpler model more. The account, the “Predictive Focus Account,” states that simpler models are better confirmed in these contexts because they make narrower, more focused predictions. The introduction presents Principle of Simplicity and the Predictive Focus Account. It defines key terms and explains the dissertation's methodology. This section also flags background issues that go beyond the scope of the dissertation. Chapter 1 investigates the philosophical history of the Predictive Focus Account, and the relationship between a model's simplicity and its “global likelihood.” On this account, the explanation of the advantage of simplicity is grounded in relations of Bayesian confirmation between competing models. That is, the advantage of simplicity is a subtle, but inherent, feature of standard Bayesian model evaluation. This chapter argues that the Predictive Focus Account is incomplete without a method for fixing prior probabilities. It proposes a new approach to fixing objective priors, the “Data Window Prior,” grounded in experimental design. The proposed prior bounds the parameters of statistical models and reigns in their predictions, which are a priori unbounded and infinitely extended. So bounded, the models have definite prediction ranges and corresponding degrees of predictive focus. I apply the Data Window Prior to the historical case of Hubble's Law from cosmology, yielding a powerful, intuitive verdict about the confirmation relations between models of varying degree of complexity. Chapter 2 contrasts the Predictive Focus Account with the more popular Bayesian method of “prior-stacking,” whereby Bayesians privilege simpler models and hypotheses with higher prior probabilities. The Predictive Focus Account has distinct advantages over the prior-stacking approach: it shows how simplicity can be favored on a posteriori, empirical grounds, and how this favoring relation depends on the nature of the extant data. Chapter 3 contrasts my account with another, based in Akaike's Information Criterion (AIC), a contemporary, non-Bayesian alternative. The AIC is a statistical model selection criterion that describes estimation error. It is designed to quantify and resist “over-fitting” the data with complex models. The main advantage of the Predictive Focus Account (and corresponding Bayesian method) is its generality. It applies to a wider range of cases and supports a broader range of inferences than the AIC.
Advisors/Committee Members: Fitelson, Branden (chair), Loewer, Barry (internal member), Maudlin, Tim (internal member), Easwaran, Kenny (outside member).
Subjects/Keywords: Simplicity (Philosophy); Prediction theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Sharber, Justin, 1. (2014). The predictive focus account of the principle of simplicity. (Doctoral Dissertation). Rutgers University. Retrieved from https://rucore.libraries.rutgers.edu/rutgers-lib/45460/
Chicago Manual of Style (16th Edition):
Sharber, Justin, 1983-. “The predictive focus account of the principle of simplicity.” 2014. Doctoral Dissertation, Rutgers University. Accessed January 23, 2021.
https://rucore.libraries.rutgers.edu/rutgers-lib/45460/.
MLA Handbook (7th Edition):
Sharber, Justin, 1983-. “The predictive focus account of the principle of simplicity.” 2014. Web. 23 Jan 2021.
Vancouver:
Sharber, Justin 1. The predictive focus account of the principle of simplicity. [Internet] [Doctoral dissertation]. Rutgers University; 2014. [cited 2021 Jan 23].
Available from: https://rucore.libraries.rutgers.edu/rutgers-lib/45460/.
Council of Science Editors:
Sharber, Justin 1. The predictive focus account of the principle of simplicity. [Doctoral Dissertation]. Rutgers University; 2014. Available from: https://rucore.libraries.rutgers.edu/rutgers-lib/45460/
Rutgers University
4.
Chang, Kun.
Topics in compositional, seasonal and spatial-temporal time series.
Degree: PhD, Statistics and Biostatistics, 2015, Rutgers University
URL: https://rucore.libraries.rutgers.edu/rutgers-lib/48411/
► This dissertation studies several topics in time series modeling. The discussion on seasonal time series, compositional time series and spatial-temporal time series brings new insight…
(more)
▼ This dissertation studies several topics in time series modeling. The discussion on seasonal time series, compositional time series and spatial-temporal time series brings new insight to the existing methods. Innovative methodologies are developed for modeling and forecasting purposes. These topics are not isolated but to naturally support each other under rigorous discussions. A variety of real examples are presented from economics, social science and geoscience areas. The second chapter introduces a new class of seasonal time series models, treating the seasonality as a stable composition through time. With the objective of forecasting the sum of the next ell observations, the concept of rolling season is adopted and a structure of rolling conditional distribution is formulated under the compositional time series framework. The probabilistic properties, the estimation and prediction, and the forecasting performance of the model are studied and demonstrated with simulation and real examples. The third chapter focuses on the discussion of compositional time series theories in multivariate models. It provides an idea to the modeling procedure of the multivariate time series that has sum constraints at each time. It also proposes a joint MLE method for threshold vector-error correction models. This chapter interprets the methodologies with an real example of the U.S. household consumption expenditures data. Threshold cointegration effects are analyzed on the U.S. real GDP growth rate. The estimation of TVECM is compared by the current two-step estimation method and the proposed joint MLE approach. Sensor allocation problem is studied in Chapter 4 under spatial-temporal models in Gaussian random fields. Given observations from existing sensors, the problem is solved by minimizing the integrated conditional variance based on different forecasting purposes. In this chapter, the time series are measured at different locations with both spatial and time series correlations. The spatial-temporal covariance structure is extensively discussed under both separable and nonseparable cases. The model is finally applied to the ozone level measurements in Harris County, Texas.
Advisors/Committee Members: Chen, Rong (chair), Xie, Minge (internal member), Xiao, Han (internal member), Cheng, Jerry (outside member).
Subjects/Keywords: Time-series analysis; Prediction theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Chang, K. (2015). Topics in compositional, seasonal and spatial-temporal time series. (Doctoral Dissertation). Rutgers University. Retrieved from https://rucore.libraries.rutgers.edu/rutgers-lib/48411/
Chicago Manual of Style (16th Edition):
Chang, Kun. “Topics in compositional, seasonal and spatial-temporal time series.” 2015. Doctoral Dissertation, Rutgers University. Accessed January 23, 2021.
https://rucore.libraries.rutgers.edu/rutgers-lib/48411/.
MLA Handbook (7th Edition):
Chang, Kun. “Topics in compositional, seasonal and spatial-temporal time series.” 2015. Web. 23 Jan 2021.
Vancouver:
Chang K. Topics in compositional, seasonal and spatial-temporal time series. [Internet] [Doctoral dissertation]. Rutgers University; 2015. [cited 2021 Jan 23].
Available from: https://rucore.libraries.rutgers.edu/rutgers-lib/48411/.
Council of Science Editors:
Chang K. Topics in compositional, seasonal and spatial-temporal time series. [Doctoral Dissertation]. Rutgers University; 2015. Available from: https://rucore.libraries.rutgers.edu/rutgers-lib/48411/
University of New South Wales
5.
Tan, Wai Hong.
Predicting the popularity of tweets using the theory of point processes.
Degree: Mathematics & Statistics, 2019, University of New South Wales
URL: http://handle.unsw.edu.au/1959.4/64234
;
https://unsworks.unsw.edu.au/fapi/datastream/unsworks:61732/SOURCE02?view=true
► This thesis focuses on the problem of predicting the tweet popularity, or the number of retweets stemming from an original tweet. We propose several prediction…
(more)
▼ This thesis focuses on the problem of predicting the tweet popularity, or the number of retweets stemming from an original tweet. We propose several
prediction methodologies using the
theory of point processes, where the
prediction of the future popularity of a tweet is based on observing the retweet time sequence up to a certain censoring time, and the
prediction performance is evaluated on a large Twitter data set. We first propose a marked point process model, termed the Marked Self-Exciting Process with Time-Dependent Excitation Function, or the MaSEPTiDE for short. The intensity process of the model is interpretable as a cluster Poisson process, which implies that the model can be simulated using the cascading algorithm similar to that used for the efficient simulation of Hawkes processes, and the
prediction can be done properly by exploiting the probabilistic properties of the model. The MaSEPTiDE approach shows highly accurate tweet popularity predictions compared to state-of-the-art approaches, especially at shorter censoring times. We further propose an inhomogeneous Poisson process model and an estimation method which utilizes internal and external knowledge, based on the times of historical retweets up to the censoring time, and the complete retweet sequences in the training data set respectively. The knowledge is combined using a novel empirical Bayes type approach, where the prior distribution for the model parameter is constructed based on the external knowledge, and the likelihood is calculated based on the internal knowledge. The mode of the posterior distribution is used as the estimator of the finite-dimensional parameter, and suitable functionals of the predictive distribution for the number of retweets implied by the estimated model are used to predict the tweet popularity. The model, termed the EB Poisson model, is found to be both efficient and accurate, with an additional advantage of being able to predict without observing any retweets. The proposed EB approach of inference is applicable on other point process models, such as the MaSEPTiDE model, to improve the
prediction performance and computational efficiency. We demonstrate this by applying the EB approach on the MaSEPTiDE model and reporting further improvements in the
prediction accuracy.
Advisors/Committee Members: Chen, Feng, Mathematics & Statistics, Faculty of Science, UNSW.
Subjects/Keywords: Prediction methodologies; Tweet popularity; Point processes theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Tan, W. H. (2019). Predicting the popularity of tweets using the theory of point processes. (Doctoral Dissertation). University of New South Wales. Retrieved from http://handle.unsw.edu.au/1959.4/64234 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:61732/SOURCE02?view=true
Chicago Manual of Style (16th Edition):
Tan, Wai Hong. “Predicting the popularity of tweets using the theory of point processes.” 2019. Doctoral Dissertation, University of New South Wales. Accessed January 23, 2021.
http://handle.unsw.edu.au/1959.4/64234 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:61732/SOURCE02?view=true.
MLA Handbook (7th Edition):
Tan, Wai Hong. “Predicting the popularity of tweets using the theory of point processes.” 2019. Web. 23 Jan 2021.
Vancouver:
Tan WH. Predicting the popularity of tweets using the theory of point processes. [Internet] [Doctoral dissertation]. University of New South Wales; 2019. [cited 2021 Jan 23].
Available from: http://handle.unsw.edu.au/1959.4/64234 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:61732/SOURCE02?view=true.
Council of Science Editors:
Tan WH. Predicting the popularity of tweets using the theory of point processes. [Doctoral Dissertation]. University of New South Wales; 2019. Available from: http://handle.unsw.edu.au/1959.4/64234 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:61732/SOURCE02?view=true
University of Saskatchewan
6.
Greschner, Michael.
Prediction of structures and properties of high-pressure solid materials using first principles methods.
Degree: 2016, University of Saskatchewan
URL: http://hdl.handle.net/10388/ETD-2016-02-2441
► The purpose of the research contained in this thesis is to allow for the prediction of new structures and properties of crystalline structures due to…
(more)
▼ The purpose of the research contained in this thesis is to allow for the
prediction of new structures and properties of crystalline structures due to the application of external pressure by using first-principles numerical computations. The body of the thesis is separated into two primary research projects.
The properties of cupric oxide (CuO) have been studied at pressures below 70 GPa, and it has been suggested that it may show room-temperature multiferroics at pressure of 20 to 40 GPa. However, at pressures above these ranges, the properties of CuO have yet to be examined thoroughly. The changes in crystal structure of CuO were examined in these high-pressure ranges. It was predicted that the ambient pressure monoclinic structure changes to a rocksalt structure and CsCl structure at high pressure. Changes in the magnetic ordering were also suggested to occur due to superexchange interactions and Jahn-Teller instabilities arising from the d-orbital electrons. Barium chloride (BaCl) has also been observed, which undergoes a similar structural change due to an s – d transition, and whose structural changes can offer further insight into the transitions observed in CuO.
Ammonia borane (NH3BH3) is known to have a crystal structure which contains the molecules in staggered conformation at low pressure. The crystalline structure of NH3BH3 was examined at high pressure, which revealed that the staggered configuration transforms to an eclipsed conformation stabilized by homopolar B–Hδ-∙∙∙ δ-H–B dihydrogen bonds. These bonds are shown to be covalent in nature, comparable in bond strength to conventional hydrogen bonds, and may allow for easier molecular hydrogen formation in hydrogen fuel storage.
Advisors/Committee Members: Yao, Yansun, Chang, Gap Soo, Tse, John S., Bowles, Richard, Moewes, Alex.
Subjects/Keywords: Condensed matter theory; First principles calculations; Structure prediction; Density functional theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Greschner, M. (2016). Prediction of structures and properties of high-pressure solid materials using first principles methods. (Thesis). University of Saskatchewan. Retrieved from http://hdl.handle.net/10388/ETD-2016-02-2441
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Greschner, Michael. “Prediction of structures and properties of high-pressure solid materials using first principles methods.” 2016. Thesis, University of Saskatchewan. Accessed January 23, 2021.
http://hdl.handle.net/10388/ETD-2016-02-2441.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Greschner, Michael. “Prediction of structures and properties of high-pressure solid materials using first principles methods.” 2016. Web. 23 Jan 2021.
Vancouver:
Greschner M. Prediction of structures and properties of high-pressure solid materials using first principles methods. [Internet] [Thesis]. University of Saskatchewan; 2016. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/10388/ETD-2016-02-2441.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Greschner M. Prediction of structures and properties of high-pressure solid materials using first principles methods. [Thesis]. University of Saskatchewan; 2016. Available from: http://hdl.handle.net/10388/ETD-2016-02-2441
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
San Jose State University
7.
Chavan, Neeraj.
Higher-order Link Prediction Using Graph Embeddings.
Degree: MS, Computer Science, 2020, San Jose State University
URL: https://scholarworks.sjsu.edu/etd_projects/934
► Link prediction is an emerging field that predicts if two nodes in a network are likely to be connected or not in the near…
(more)
▼ Link
prediction is an emerging field that predicts if two nodes in a network are likely to be connected or not in the near future. Networks model real-world systems using pairwise interactions of nodes. However, many of these interactions may involve more than two nodes or entities simultaneously. For example, social interactions often occur in groups of people, research collaborations are among more than two authors, and biological networks describe interactions of a group of proteins. An interaction that consists of more than two entities is called a higher-order structure. Predicting the occurrence of such higher-order structures helps us solve problems on various disciplines, such as social network analysis, drug combinations research, and news topic connections. Moreover, we can use our methods to get more knowledge about news topics during the COVID-19 pandemic.
Higher-order link
prediction can be accomplished using neural networks and other machine learning techniques. The primary focus of this project is to explore repre- sentations of three-node interactions, called triangles (a special case of higher-order structure). We propose new methods to embed triangles: by generalizing node2vec algorithm using different operators to learn an embedding for a triangle, and by using 1-hop subgraphs of the triangles to learn embeddings using graph2vec algorithm and graph neural networks. The performance of these techniques is evaluated against the benchmark scores on various datasets used in the bibliography. From the results, it is observed that the node2vec based triangle embedding algorithm performs better or similar on most of the datasets compared to benchmark models.
Advisors/Committee Members: Katerina Potika, Chris Pollett, William Andreopoulos.
Subjects/Keywords: link prediction; triangle prediction; node2vec; graph2vec; graph neural networks; Other Computer Sciences; Theory and Algorithms
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Chavan, N. (2020). Higher-order Link Prediction Using Graph Embeddings. (Masters Thesis). San Jose State University. Retrieved from https://scholarworks.sjsu.edu/etd_projects/934
Chicago Manual of Style (16th Edition):
Chavan, Neeraj. “Higher-order Link Prediction Using Graph Embeddings.” 2020. Masters Thesis, San Jose State University. Accessed January 23, 2021.
https://scholarworks.sjsu.edu/etd_projects/934.
MLA Handbook (7th Edition):
Chavan, Neeraj. “Higher-order Link Prediction Using Graph Embeddings.” 2020. Web. 23 Jan 2021.
Vancouver:
Chavan N. Higher-order Link Prediction Using Graph Embeddings. [Internet] [Masters thesis]. San Jose State University; 2020. [cited 2021 Jan 23].
Available from: https://scholarworks.sjsu.edu/etd_projects/934.
Council of Science Editors:
Chavan N. Higher-order Link Prediction Using Graph Embeddings. [Masters Thesis]. San Jose State University; 2020. Available from: https://scholarworks.sjsu.edu/etd_projects/934
Penn State University
8.
Akcay, Samet.
link age: a factor in link prediction in a social network.
Degree: 2015, Penn State University
URL: https://submit-etda.libraries.psu.edu/catalog/25789
► This work extends a previous one that investigated link age and its effect on network evolu- tion. Whether aging adversely influences prediction power of links…
(more)
▼ This work extends a previous one that investigated link age and its effect on network evolu- tion. Whether aging adversely influences
prediction power of links in network evolution is the fundamental question partially answered in the previous work. Additionally, this study argues whether reliable old connections in a network have a great impact on future link predictions. One of our hypotheses is that aging of a link is a crucial factor in link
prediction. The other one is that
prediction power of a link usually lessens over time. Using logistic regression and mixture extension, younger links are observed to dominate the link
prediction process in most cases. However, this is not always the case. We cannot ignore the links that are old but still powerful. In addition to
prediction power of the links, using a mixture model improves the overall link
prediction accuracy. The findings of this research support the implications of the previous work that some old and unstable links might be removed from the network.
Advisors/Committee Members: David Jonathan Miller, Thesis Advisor/Co-Advisor.
Subjects/Keywords: Social Network; Link Prediction; Prediction Power; Network Theory; Mixture Model; Logistic Regression
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Akcay, S. (2015). link age: a factor in link prediction in a social network. (Thesis). Penn State University. Retrieved from https://submit-etda.libraries.psu.edu/catalog/25789
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Akcay, Samet. “link age: a factor in link prediction in a social network.” 2015. Thesis, Penn State University. Accessed January 23, 2021.
https://submit-etda.libraries.psu.edu/catalog/25789.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Akcay, Samet. “link age: a factor in link prediction in a social network.” 2015. Web. 23 Jan 2021.
Vancouver:
Akcay S. link age: a factor in link prediction in a social network. [Internet] [Thesis]. Penn State University; 2015. [cited 2021 Jan 23].
Available from: https://submit-etda.libraries.psu.edu/catalog/25789.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Akcay S. link age: a factor in link prediction in a social network. [Thesis]. Penn State University; 2015. Available from: https://submit-etda.libraries.psu.edu/catalog/25789
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Universiteit Utrecht
9.
Davidse, J.
Polderen over dijken.
Degree: 2015, Universiteit Utrecht
URL: http://dspace.library.uu.nl:8080/handle/1874/308117
► Het huidige onderzoek is ontstaan vanuit een vraag van Waternet. Namelijk hoe de organisatie met behulp van interactieve online communicatie meer betrokkenheid kan creëren bij…
(more)
▼ Het huidige onderzoek is ontstaan vanuit een vraag van Waternet. Namelijk hoe de organisatie met behulp van interactieve online communicatie meer betrokkenheid kan creëren bij dijkbewoners tijdens de uitvoeringsfase van een dijkverbetering. De organisatie wil enerzijds meegaan in de digitalisering die in Nederland een steeds grotere rol speelt. Anderzijds is het voor Waternet belangrijk om haar klanten zo goed mogelijk in hun communicatiebehoeften te voorzien. Om Waternet een advies te kunnen geven over dit vraagstuk is in dit onderzoek de volgende hoofdvraag opgesteld: ‘Welke communicatiemiddelen lenen zich goed en minder goed voor het creëren van betrokkenheid bij bewoners tijdens de uitvoeringsfase van een dijkverbetering?’ Voor de beantwoording van deze vraag is naar één specifiek dijkverbeteringsproject gekeken dat bij aanvang van dit onderzoek (september 2014) bijna in de uitvoeringsfase zat. Binnen deze dijkverbetering is de communicatiebehoefte van bewoners bevraagd. Hiervoor zijn vijf interviews afgenomen bij dijkbewoners. Daarna is naar alle huishoudens een enquête uitgestuurd om te bevragen welke informatie dijkbewoners via welke communicatiemiddelen willen ontvangen en om te meten hoe betrokken deze bewoners zijn. Ook zijn drie medewerkers van Waternet geïnterviewd die bij de dijkverbetering betrokken zijn. Verder is er informatie verzameld vanuit onderzoeksliteratuur over gedragsverandering en mediafunctionaliteiten en vanuit interne documenten van Waternet. In dit onderzoek is eerst vastgesteld welke soorten informatie Waternet moet delen en daarna is gekeken welke communicatiemiddelen daar goed of minder goed bij aansluiten.
Advisors/Committee Members: Holleman, B..
Subjects/Keywords: Media Synchronicity Theory; Intergrative Model of Behavioral Prediction; betrokkenheid
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Davidse, J. (2015). Polderen over dijken. (Masters Thesis). Universiteit Utrecht. Retrieved from http://dspace.library.uu.nl:8080/handle/1874/308117
Chicago Manual of Style (16th Edition):
Davidse, J. “Polderen over dijken.” 2015. Masters Thesis, Universiteit Utrecht. Accessed January 23, 2021.
http://dspace.library.uu.nl:8080/handle/1874/308117.
MLA Handbook (7th Edition):
Davidse, J. “Polderen over dijken.” 2015. Web. 23 Jan 2021.
Vancouver:
Davidse J. Polderen over dijken. [Internet] [Masters thesis]. Universiteit Utrecht; 2015. [cited 2021 Jan 23].
Available from: http://dspace.library.uu.nl:8080/handle/1874/308117.
Council of Science Editors:
Davidse J. Polderen over dijken. [Masters Thesis]. Universiteit Utrecht; 2015. Available from: http://dspace.library.uu.nl:8080/handle/1874/308117
University of Michigan
10.
Kong, Yuqing.
Eliciting and Aggregating Information: An Information Theoretic Approach.
Degree: PhD, Computer Science & Engineering, 2018, University of Michigan
URL: http://hdl.handle.net/2027.42/145809
► Crowdsourcing – outsourcing tasks to a crowd of workers (e.g. Amazon Mechanical Turk, peer grading for massive open online courseware (MOOCs), scholarly peer review, and Yahoo…
(more)
▼ Crowdsourcing – outsourcing tasks to a crowd of workers (e.g. Amazon Mechanical Turk, peer grading for massive open online courseware (MOOCs), scholarly peer review, and Yahoo answers) – is a fast, cheap, and effective method for performing simple tasks even at large scales. Two central problems in this area are:
Information Elicitation: how to design reward systems that incentivize high quality feedback from agents; and
Information Aggregation: how to aggregate the collected feedback to obtain a high quality forecast.
This thesis shows that the combination of game
theory, information
theory, and learning
theory can bring a unified framework to both of the central problems in crowdsourcing area. This thesis builds a natural connection between information elicitation and information aggregation, distills the essence of eliciting and aggregating information to the design of proper information measurements and applies the information measurements to both the central problems:
In the setting where information cannot be verified, this thesis proposes a simple yet powerful information theoretical framework, the emph{Mutual Information Paradigm (MIP)}, for information elicitation mechanisms. The framework pays every agent a measure of mutual information between her signal and a peer's signal. The mutual information measurement is required to have the key property that any ``data processing'' on the two random variables will decrease the mutual information between them. We identify such information measures that generalize Shannon mutual information. MIP overcomes the two main challenges in information elicitation without verification: (1) how to incentivize effort and avoid agents colluding to report random or identical responses (2) how to motivate agents who believe they are in the minority to report truthfully.
To elicit expertise without verification, this thesis also defines a natural model for this setting based on the assumption that emph{more sophisticated agents know the beliefs of less sophisticated agents} and extends MIP to a mechanism design framework, the emph{Hierarchical Mutual Information Paradigm (HMIP)}, for this setting.
Aided by the information measures and the frameworks, this thesis (1) designs several novel information elicitation mechanisms (e.g. the disagreement mechanism, the f-mutual information mechanism, the multi-hierarchical mutual information mechanism, the common ground mechanism) in various of settings such that honesty and efforts are incentivized and expertise is identified; (2) addresses an important unsupervised learning problem – co-training by reducing it to an information elicitation problem – forecast elicitation without verification.
Advisors/Committee Members: Schoenebeck, Grant (committee member), Liu, Mingyan (committee member), Lasecki, Walter (committee member), Parkes, David (committee member).
Subjects/Keywords: Peer prediction; Information theory; Mechanism design; Unsupervised learning; Computer Science; Engineering
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kong, Y. (2018). Eliciting and Aggregating Information: An Information Theoretic Approach. (Doctoral Dissertation). University of Michigan. Retrieved from http://hdl.handle.net/2027.42/145809
Chicago Manual of Style (16th Edition):
Kong, Yuqing. “Eliciting and Aggregating Information: An Information Theoretic Approach.” 2018. Doctoral Dissertation, University of Michigan. Accessed January 23, 2021.
http://hdl.handle.net/2027.42/145809.
MLA Handbook (7th Edition):
Kong, Yuqing. “Eliciting and Aggregating Information: An Information Theoretic Approach.” 2018. Web. 23 Jan 2021.
Vancouver:
Kong Y. Eliciting and Aggregating Information: An Information Theoretic Approach. [Internet] [Doctoral dissertation]. University of Michigan; 2018. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/2027.42/145809.
Council of Science Editors:
Kong Y. Eliciting and Aggregating Information: An Information Theoretic Approach. [Doctoral Dissertation]. University of Michigan; 2018. Available from: http://hdl.handle.net/2027.42/145809
11.
Frach, Roland.
Expanding the scope of integral equation-based solvation theory.
Degree: 2015, Technische Universität Dortmund
URL: http://dx.doi.org/10.17877/DE290R-16566
► Implicit solvation models are used to predict and to understand various properties of solutions within feasible time scales. But common implicit approaches ignore the granularity…
(more)
▼ Implicit solvation models are used to predict and to understand various properties of solutions within feasible time scales. But common implicit approaches ignore the granularity of the solvent and fail to describe substantial directional interactions like hydrogen bonds. A different way to calculate various properties of solvents without that retains this features is presented in this work, the reference interaction site model (RISM). Thereby the solvent is characterized by its pair distribution function, which is a measure for the near-order of the solvent particles. Furthermore the pair distribution functions are connected within the RISM approach with the free energy of solvation. Combining the RISM approach with quantummechanical precision for the solute leads to the so-called embedded cluster reference interaction site model, EC-RISM. This is achieved by application of a self-consistent approach for both parts that are connected with a
cluster of embedded point charges, which describes the solvent-solute interaction. By now the EC-RISM methodology was only applied for studies of free energies and related subjects of dipolar, mostly aqueous solutions. The applicability of EC-RISM for different properties of solutions as well as for nondipolar solvents was so far not ensured in the past. Here, two important aspects are in the focus; on the one hand, NMR chemical shifts are calculated to test whether the EC-RISM approach properly describes the solvent influence on the wave function of the solute and to test the wave function itself. On the other hand benzene and hexafluorobenzene models are developed to research if these complex and very similar solvents are distinguishable with integral equation theories like RISM. Furthermore these models are applied for the investigation of a chemical reaction that shows a stereoselectivity enhancement that is caused by the application of hexafluorobenzene compared to benzene.
These investigations show that EC-RISM systematically improves the chemical shifts in aqueous solutions and therefore displays the adequacy of the corresponding wave function. Additionally it is confirmed that benzene and hexafluorobenzene are properly described and that even the stereoselectivity of the previously mentioned chemical reaction is correctly predicted. Thereby the different solvent influences are separated, analyzed, considered and discussed, whereas the relevance of dispersive and multipolar parts is elucidated.
Advisors/Committee Members: Kast, Stefan Michael (advisor), Winter, Roland (referee).
Subjects/Keywords: EC-RISM; chemical shift prediction; nondipolar solvation; liquid state theory; 540
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Frach, R. (2015). Expanding the scope of integral equation-based solvation theory. (Doctoral Dissertation). Technische Universität Dortmund. Retrieved from http://dx.doi.org/10.17877/DE290R-16566
Chicago Manual of Style (16th Edition):
Frach, Roland. “Expanding the scope of integral equation-based solvation theory.” 2015. Doctoral Dissertation, Technische Universität Dortmund. Accessed January 23, 2021.
http://dx.doi.org/10.17877/DE290R-16566.
MLA Handbook (7th Edition):
Frach, Roland. “Expanding the scope of integral equation-based solvation theory.” 2015. Web. 23 Jan 2021.
Vancouver:
Frach R. Expanding the scope of integral equation-based solvation theory. [Internet] [Doctoral dissertation]. Technische Universität Dortmund; 2015. [cited 2021 Jan 23].
Available from: http://dx.doi.org/10.17877/DE290R-16566.
Council of Science Editors:
Frach R. Expanding the scope of integral equation-based solvation theory. [Doctoral Dissertation]. Technische Universität Dortmund; 2015. Available from: http://dx.doi.org/10.17877/DE290R-16566
University of Cambridge
12.
Nelson, Joseph Richard.
Crystal structure prediction at high pressures: stability, superconductivity and superionicity.
Degree: PhD, 2017, University of Cambridge
URL: https://www.repository.cam.ac.uk/handle/1810/268482
► The physical and chemical properties of materials are intimately related to their underlying crystal structure: the detailed arrangement of atoms and chemical bonds within. This…
(more)
▼ The physical and chemical properties of materials are intimately related to their underlying crystal structure: the detailed arrangement of atoms and chemical bonds within. This thesis uses computational methods to predict crystal structure, with a particular focus on structures and stable phases that emerge at high pressure. We explore three distinct systems.
We first apply the ab initio random structure searching (AIRSS) technique and density functional theory (DFT) calculations to investigate the high-pressure behaviour of beryllium, magnesium and calcium difluorides. We find that beryllium fluoride is extensively polymorphic at low pressures, and predict two new phases for this compound - the silica moganite and CaCl2 structures - to be stable over the wide pressure range 12-57 GPa. For magnesium fluoride, our results show that the orthorhombic `O-I' TiO2 structure (Pbca, Z=8) is stable for this compound between 40 and 44 GPa. Our searches find no new phases at the static-lattice level for calcium difluoride between 0 and 70 GPa; however, a phase with P6̅2m symmetry is energetically close to stability over this pressure range, and our calculations predict that this phase is stabilised at high temperature. The P6̅2m structure exhibits an unstable phonon mode at large volumes which may signal a transition to a superionic state at high temperatures. The Group-II difluorides are isoelectronic to a number of other AB2-type compounds such as SiO2 and TiO2, and we discuss our results in light of these similarities.
Compressed hydrogen sulfide (H2S) has recently attracted experimental and theoretical interest due to the observation of high-temperature superconductivity in this compound (Tc = 203 K) at high pressure (155 GPa). We use the AIRSS technique and DFT calculations to determine the stable phases and chemical stoichiometries formed in the hydrogen-sulfur system as a function of pressure. We find that this system supports numerous stable compounds: H3S, H7S3, H2S, H3S2, H4S3, H2S3 and HS2, at various pressures. Working as part of a collaboration, our predicted H3S and H4S3 structures are shown to be consistent with XRD data for this system, with H4S3 identified as a major decomposition product of H2S in the lead-up to the superconducting state.
Calcium and oxygen are two elements of generally high terrestrial and cosmic abundance, and we explore structures of calcium peroxide (CaO2) in the pressure range 0-200 GPa. Stable structures for CaO2 with C2/c, I4/mcm and P21/c symmetries emerge at pressures below 40 GPa, which we find are thermodynamically stable against decomposition into CaO and O2. The stability of CaO2 with respect to decomposition increases with pressure, with peak stability occurring at the CaO B1-B2 phase transition at 65 GPa. Phonon calculations using the quasiharmonic approximation show that CaO2 is a stable oxide of calcium at mantle temperatures and pressures, highlighting…
Subjects/Keywords: Density functional theory; High-pressure physics; Crystal structure prediction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Nelson, J. R. (2017). Crystal structure prediction at high pressures: stability, superconductivity and superionicity. (Doctoral Dissertation). University of Cambridge. Retrieved from https://www.repository.cam.ac.uk/handle/1810/268482
Chicago Manual of Style (16th Edition):
Nelson, Joseph Richard. “Crystal structure prediction at high pressures: stability, superconductivity and superionicity.” 2017. Doctoral Dissertation, University of Cambridge. Accessed January 23, 2021.
https://www.repository.cam.ac.uk/handle/1810/268482.
MLA Handbook (7th Edition):
Nelson, Joseph Richard. “Crystal structure prediction at high pressures: stability, superconductivity and superionicity.” 2017. Web. 23 Jan 2021.
Vancouver:
Nelson JR. Crystal structure prediction at high pressures: stability, superconductivity and superionicity. [Internet] [Doctoral dissertation]. University of Cambridge; 2017. [cited 2021 Jan 23].
Available from: https://www.repository.cam.ac.uk/handle/1810/268482.
Council of Science Editors:
Nelson JR. Crystal structure prediction at high pressures: stability, superconductivity and superionicity. [Doctoral Dissertation]. University of Cambridge; 2017. Available from: https://www.repository.cam.ac.uk/handle/1810/268482
13.
Mayo, Martin.
Ab Initio Anode Materials Discovery for Li- and Na-Ion Batteries.
Degree: PhD, 2018, University of Cambridge
URL: https://www.repository.cam.ac.uk/handle/1810/270545
► This thesis uses first principles techniques, mainly the ab initio random structure searching method (AIRSS), to study anode materials for lithium- and sodium- ion batteries…
(more)
▼ This thesis uses first principles techniques, mainly the ab initio random structure searching method (AIRSS), to study anode materials for lithium- and sodium- ion batteries (LIBs and NIBs, respectively). Initial work relates to a theoretical structure prediction study of the lithium and sodium phosphide systems in the context of phosphorus anodes as candidates for LIBs and NIBs. The work reveals new Li-P and Na-P phases, some of which can be used to better interpret previous experimental results. By combining AIRSS searches with a high-throughput screening search from structures in the Inorganic Crystal Structure Database (ICSD), regions in the phase diagram are correlated to different ionic motifs and NMR chemical shielding is predicted from first principles. An electronic structure analysis of the Li-P and Na-P compounds is performed and its implication on the anode performance is discussed. The study is concluded by exploring the addition of aluminium dopants to the Li-P compounds to improve the electronic conductivity of the system.
The following work deals with a study of tin anodes for NIBs. The structure prediction study yields a variety of new phases; of particular interest is a new NaSn2 phase predicted by AIRSS. This phase plays a crucial role in understanding the alloying mechanism of high-capacity tin anodes, work which was done in collaboration with experimental colleagues. Our predicted theoretical voltages give excellent agreement with the experimental electrochemical cycling curve. First principles molecular dynamics is used to propose an amorphous Na1Sn1 model which, in addition to the newly derived NaSn2 phase, provides help in revealing the electrochemical processes.
In the subsequent work, we study Li-Sn and Li-Sb intermetallics in the context of alloy anodes for LIBs. A rich phase diagram of Li-Sn is present, exhibiting a variety of new phases. The calculated voltages show excellent agreement with previously reported cycling measurements and a consistent structural evolution of Li-Sn phases as Li concentration increases is revealed.
The study concluded by calculating NMR parameters on the hexagonal- and cubic-Li3Sb phases which shed light on the interpretation of reported experimental data.
We conclude with a structure prediction study of the pseudobinary Li-FeS2 system, where FeS2 is considered as a potential high-capacity electrochemical energy storage system. Our first principles calculations of intermediate structures help to elucidate the mechanism of charge storage observed by our experimental collaborators via it{in operando} studies.
Subjects/Keywords: batteries; anodes; structure prediction; Density-functional theory; NMR; GIPAW
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Mayo, M. (2018). Ab Initio Anode Materials Discovery for Li- and Na-Ion Batteries. (Doctoral Dissertation). University of Cambridge. Retrieved from https://www.repository.cam.ac.uk/handle/1810/270545
Chicago Manual of Style (16th Edition):
Mayo, Martin. “Ab Initio Anode Materials Discovery for Li- and Na-Ion Batteries.” 2018. Doctoral Dissertation, University of Cambridge. Accessed January 23, 2021.
https://www.repository.cam.ac.uk/handle/1810/270545.
MLA Handbook (7th Edition):
Mayo, Martin. “Ab Initio Anode Materials Discovery for Li- and Na-Ion Batteries.” 2018. Web. 23 Jan 2021.
Vancouver:
Mayo M. Ab Initio Anode Materials Discovery for Li- and Na-Ion Batteries. [Internet] [Doctoral dissertation]. University of Cambridge; 2018. [cited 2021 Jan 23].
Available from: https://www.repository.cam.ac.uk/handle/1810/270545.
Council of Science Editors:
Mayo M. Ab Initio Anode Materials Discovery for Li- and Na-Ion Batteries. [Doctoral Dissertation]. University of Cambridge; 2018. Available from: https://www.repository.cam.ac.uk/handle/1810/270545
University of California – San Francisco
14.
Shih, Jonathan Yih.
Spectrotemporal Processing in the Auditory Thalamus and Cortex.
Degree: Bioengineering, 2012, University of California – San Francisco
URL: http://www.escholarship.org/uc/item/6w8490hg
► Spectrotemporal receptive fields are useful for determining properties such as an auditory neuron's characteristic frequency, response latency, and spectral and temporal modulation preferences. Above all,…
(more)
▼ Spectrotemporal receptive fields are useful for determining properties such as an auditory neuron's characteristic frequency, response latency, and spectral and temporal modulation preferences. Above all, spectrotemporal receptive fields represent the specific stimulus features that elicit spiking activity. Unfortunately, most classic receptive field techniques, such as the spike-triggered average (STA), are only capable of capturing single stimulus features, and recent studies have shown that auditory cortical neurons are simultaneously influenced by multiple stimulus features.In this study, maximally informative dimensions (MID) analysis, a multi-feature receptive field technique, was applied to neurons in the auditory thalamus and cortex. Specifically, thalamic neurons from the ventral division of the medial geniculate body (MGBv) and cortical neurons from the anterior auditory field (AAF) and primary auditory cortex (A1) were examined. Our results showed that whereas most A1 neurons displayed significant dual-feature processing characteristics, two-feature MID models failed to yield improved response predictions over one-feature MID models for most neurons in MGBv and AAF.In neurons that did show evidence of dual-feature processing, the spectrotemporal properties of each of the MID features were examined. Although the first MID feature component (MID1) was highly similar to the STA, the second MID feature component (MID2) captured stimulus processing not represented in single-feature models. MID2 features generally occurred at longer latencies and integrated stimulus information over a broader spectral range.Interestingly, however, the two-feature MID model was rarely able to capture the entirety of a neuron's predictable response. We hypothesized that this was because auditory neurons use temporal coding that cannot be captured by receptive field techniques that assume independent spiking. To test this hypothesis, we examined the encoding properties of the simplest temporal pattern: the interspike interval (ISI). The findings demonstrated that pairs of spikes with short ISIs constituted a source of highly reliable, easily decoded stimulus information that contributed disproportionately to the stimulus encoding of A1 neurons.Taken together, these results provide evidence of increasing multi-dimensional processing as information ascends the auditory pathway and illuminate the limitations of independent-spiking analysis techniques in sensory areas that display significant temporal coding.
Subjects/Keywords: Neurosciences; Auditory; Cortex; Information Theory; Prediction; Receptive Field; Thalamus
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Shih, J. Y. (2012). Spectrotemporal Processing in the Auditory Thalamus and Cortex. (Thesis). University of California – San Francisco. Retrieved from http://www.escholarship.org/uc/item/6w8490hg
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Shih, Jonathan Yih. “Spectrotemporal Processing in the Auditory Thalamus and Cortex.” 2012. Thesis, University of California – San Francisco. Accessed January 23, 2021.
http://www.escholarship.org/uc/item/6w8490hg.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Shih, Jonathan Yih. “Spectrotemporal Processing in the Auditory Thalamus and Cortex.” 2012. Web. 23 Jan 2021.
Vancouver:
Shih JY. Spectrotemporal Processing in the Auditory Thalamus and Cortex. [Internet] [Thesis]. University of California – San Francisco; 2012. [cited 2021 Jan 23].
Available from: http://www.escholarship.org/uc/item/6w8490hg.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Shih JY. Spectrotemporal Processing in the Auditory Thalamus and Cortex. [Thesis]. University of California – San Francisco; 2012. Available from: http://www.escholarship.org/uc/item/6w8490hg
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Hong Kong University of Science and Technology
15.
Leung, Chi Chung.
Improving prediction by non-linear techniques.
Degree: 1999, Hong Kong University of Science and Technology
URL: http://repository.ust.hk/ir/Record/1783.1-5082
;
https://doi.org/10.14711/thesis-b645944
;
http://repository.ust.hk/ir/bitstream/1783.1-5082/1/th_redirect.html
► It is observed that the predictivity is larger when predicting the change in absolute magnitude than when predicting the actual value in the weather forecasting,…
(more)
▼ It is observed that the predictivity is larger when predicting the change in absolute magnitude than when predicting the actual value in the weather forecasting, such as daily temperature and monthly rainful are easier to be predicted than the actual value. In this thesis, we investigate this observation by analyzing two specific stationary processes which are often used for modeling different physical phenomena, namely, the stationary AR(1) process and the stationary AR(2) process.
Subjects/Keywords: Prediction theory
; Nonlinear functional analysis
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Leung, C. C. (1999). Improving prediction by non-linear techniques. (Thesis). Hong Kong University of Science and Technology. Retrieved from http://repository.ust.hk/ir/Record/1783.1-5082 ; https://doi.org/10.14711/thesis-b645944 ; http://repository.ust.hk/ir/bitstream/1783.1-5082/1/th_redirect.html
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Leung, Chi Chung. “Improving prediction by non-linear techniques.” 1999. Thesis, Hong Kong University of Science and Technology. Accessed January 23, 2021.
http://repository.ust.hk/ir/Record/1783.1-5082 ; https://doi.org/10.14711/thesis-b645944 ; http://repository.ust.hk/ir/bitstream/1783.1-5082/1/th_redirect.html.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Leung, Chi Chung. “Improving prediction by non-linear techniques.” 1999. Web. 23 Jan 2021.
Vancouver:
Leung CC. Improving prediction by non-linear techniques. [Internet] [Thesis]. Hong Kong University of Science and Technology; 1999. [cited 2021 Jan 23].
Available from: http://repository.ust.hk/ir/Record/1783.1-5082 ; https://doi.org/10.14711/thesis-b645944 ; http://repository.ust.hk/ir/bitstream/1783.1-5082/1/th_redirect.html.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Leung CC. Improving prediction by non-linear techniques. [Thesis]. Hong Kong University of Science and Technology; 1999. Available from: http://repository.ust.hk/ir/Record/1783.1-5082 ; https://doi.org/10.14711/thesis-b645944 ; http://repository.ust.hk/ir/bitstream/1783.1-5082/1/th_redirect.html
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Rice University
16.
Kim, Bobby Lee.
Optimization of predictive energy landscapes for membrane and globular protein structure prediction.
Degree: PhD, Natural Sciences, 2015, Rice University
URL: http://hdl.handle.net/1911/88336
► This thesis discusses recent results using the Associative-memory, Water-mediated, Structure and Energy Model (AWSEM), an optimized, coarse-grained molecular dynamics model. AWSEM and its membrane protein…
(more)
▼ This thesis discusses recent results using the Associative-memory, Water-mediated, Structure and Energy Model (AWSEM), an optimized, coarse-grained molecular dynamics model. AWSEM and its membrane protein extension, AWSEM-membrane, are capable of de novo protein structure
prediction and through the use of statistical estimators, allow construction of free energy landscapes which can provide insight about the dynamics of protein systems. We review the origins of energy landscape
theory and how one can learn energy functions using the results of spin glass-inspired statistical mechanics models. We explore the similarities and differences between the energy landscapes of proteins that have been selected by nature and those of some proteins designed by humans. We also study how robust the folding of these designs would be to the simplification of the sequences using fewer amino acid types. Using an optimized extension of AWSEM, AWSEM-membrane, we explore the hypothesis that the folding landscapes of membrane proteins are funneled once the proteins’ topology within the membrane is established. We also show that the AWSEM-membrane force field is able to sample near native binding interfaces of several oligomeric systems.
Advisors/Committee Members: Wolynes, Peter G. (advisor), Onuchic, José N (committee member), Clementi, Cecilia (committee member).
Subjects/Keywords: protein folding; protein structure prediction; energy landscape theory; molecular dynamics
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kim, B. L. (2015). Optimization of predictive energy landscapes for membrane and globular protein structure prediction. (Doctoral Dissertation). Rice University. Retrieved from http://hdl.handle.net/1911/88336
Chicago Manual of Style (16th Edition):
Kim, Bobby Lee. “Optimization of predictive energy landscapes for membrane and globular protein structure prediction.” 2015. Doctoral Dissertation, Rice University. Accessed January 23, 2021.
http://hdl.handle.net/1911/88336.
MLA Handbook (7th Edition):
Kim, Bobby Lee. “Optimization of predictive energy landscapes for membrane and globular protein structure prediction.” 2015. Web. 23 Jan 2021.
Vancouver:
Kim BL. Optimization of predictive energy landscapes for membrane and globular protein structure prediction. [Internet] [Doctoral dissertation]. Rice University; 2015. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/1911/88336.
Council of Science Editors:
Kim BL. Optimization of predictive energy landscapes for membrane and globular protein structure prediction. [Doctoral Dissertation]. Rice University; 2015. Available from: http://hdl.handle.net/1911/88336
Michigan State University
17.
Phoha, Shashi Prabha, 1948-.
On algorithms for nonlinear prediction.
Degree: PhD, 1976, Michigan State University
URL: http://etd.lib.msu.edu/islandora/object/etd:35817
Subjects/Keywords: Prediction theory; Algorithms; Stochastic processes
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Phoha, Shashi Prabha, 1. (1976). On algorithms for nonlinear prediction. (Doctoral Dissertation). Michigan State University. Retrieved from http://etd.lib.msu.edu/islandora/object/etd:35817
Chicago Manual of Style (16th Edition):
Phoha, Shashi Prabha, 1948-. “On algorithms for nonlinear prediction.” 1976. Doctoral Dissertation, Michigan State University. Accessed January 23, 2021.
http://etd.lib.msu.edu/islandora/object/etd:35817.
MLA Handbook (7th Edition):
Phoha, Shashi Prabha, 1948-. “On algorithms for nonlinear prediction.” 1976. Web. 23 Jan 2021.
Vancouver:
Phoha, Shashi Prabha 1. On algorithms for nonlinear prediction. [Internet] [Doctoral dissertation]. Michigan State University; 1976. [cited 2021 Jan 23].
Available from: http://etd.lib.msu.edu/islandora/object/etd:35817.
Council of Science Editors:
Phoha, Shashi Prabha 1. On algorithms for nonlinear prediction. [Doctoral Dissertation]. Michigan State University; 1976. Available from: http://etd.lib.msu.edu/islandora/object/etd:35817
Montana State University
18.
Jonca, Andrzej Wilhelm.
Prediction bands for ill-posed problems.
Degree: PhD, College of Letters & Science, 1988, Montana State University
URL: https://scholarworks.montana.edu/xmlui/handle/1/6558
Subjects/Keywords: Linear operators.; Prediction theory.
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Jonca, A. W. (1988). Prediction bands for ill-posed problems. (Doctoral Dissertation). Montana State University. Retrieved from https://scholarworks.montana.edu/xmlui/handle/1/6558
Chicago Manual of Style (16th Edition):
Jonca, Andrzej Wilhelm. “Prediction bands for ill-posed problems.” 1988. Doctoral Dissertation, Montana State University. Accessed January 23, 2021.
https://scholarworks.montana.edu/xmlui/handle/1/6558.
MLA Handbook (7th Edition):
Jonca, Andrzej Wilhelm. “Prediction bands for ill-posed problems.” 1988. Web. 23 Jan 2021.
Vancouver:
Jonca AW. Prediction bands for ill-posed problems. [Internet] [Doctoral dissertation]. Montana State University; 1988. [cited 2021 Jan 23].
Available from: https://scholarworks.montana.edu/xmlui/handle/1/6558.
Council of Science Editors:
Jonca AW. Prediction bands for ill-posed problems. [Doctoral Dissertation]. Montana State University; 1988. Available from: https://scholarworks.montana.edu/xmlui/handle/1/6558
University of Notre Dame
19.
Ryan N. Lichtenwalter.
Network Analysis and Link Prediction: Effective and
Meaningful Modeling and Evaluation</h1>.
Degree: Computer Science and Engineering, 2012, University of Notre Dame
URL: https://curate.nd.edu/show/fj23611103z
► Link prediction is succinctly stated as identifying unobserved links in a network. It has important applications ranging from recommending beneficial relationships in social networks…
(more)
▼ Link
prediction is succinctly stated as
identifying unobserved links in a network. It has important
applications ranging from recommending beneficial relationships in
social networks to discovering new protein-protein interactions in
biological networks. This dissertation primarily focuses on link
prediction in homogeneous, single-relational networks, but it also
introduces new techniques for handling multi-relational networks.
We identify what we view as the three principal components of
effective link
prediction: high-performance algorithms and methods,
proper evaluation, and computational scalability. Performance is
the natural requirement that the predictive models provide usably
correct outputs. Evaluation is the surprisingly difficult question
of how to determine the correctness of a model in order to compare
models and develop an expectation of effectiveness in real
deployment. Computational scalability is necessary to obtain output
from a link
prediction framework in a reasonable amount of time on
large networks. Each of these three components poses significant
challenges, and it is reasonable to say that any of these
challenges individually can stand in the way of the proliferation
of link
prediction techniques for useful research and domain
applications.
Advisors/Committee Members: Nitesh V. Chawla, Committee Chair, David S. Hachen Jr., Committee Member, Zoltan Toroczkai, Committee Member, Douglas Thain, Committee Member.
Subjects/Keywords: link analysis; data mining; link prediction; networks; graph theory; classification
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Lichtenwalter, R. N. (2012). Network Analysis and Link Prediction: Effective and
Meaningful Modeling and Evaluation</h1>. (Thesis). University of Notre Dame. Retrieved from https://curate.nd.edu/show/fj23611103z
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Lichtenwalter, Ryan N.. “Network Analysis and Link Prediction: Effective and
Meaningful Modeling and Evaluation</h1>.” 2012. Thesis, University of Notre Dame. Accessed January 23, 2021.
https://curate.nd.edu/show/fj23611103z.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Lichtenwalter, Ryan N.. “Network Analysis and Link Prediction: Effective and
Meaningful Modeling and Evaluation</h1>.” 2012. Web. 23 Jan 2021.
Vancouver:
Lichtenwalter RN. Network Analysis and Link Prediction: Effective and
Meaningful Modeling and Evaluation</h1>. [Internet] [Thesis]. University of Notre Dame; 2012. [cited 2021 Jan 23].
Available from: https://curate.nd.edu/show/fj23611103z.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Lichtenwalter RN. Network Analysis and Link Prediction: Effective and
Meaningful Modeling and Evaluation</h1>. [Thesis]. University of Notre Dame; 2012. Available from: https://curate.nd.edu/show/fj23611103z
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Clemson University
20.
Canonico, Lorenzo Barberis.
Human-Machine Teamwork: An Exploration of Multi-Agent Systems, Team Cognition, and Collective Intelligence.
Degree: PhD, School of Computing, 2019, Clemson University
URL: https://tigerprints.clemson.edu/all_dissertations/2490
► One of the major ways through which humans overcome complex challenges is teamwork. When humans share knowledge and information, and cooperate and coordinate towards…
(more)
▼ One of the major ways through which humans overcome complex challenges is teamwork. When humans share knowledge and information, and cooperate and coordinate towards shared goals, they overcome their individual limitations and achieve better solutions to difficult problems. The rise of artificial intelligence provides a unique opportunity to study teamwork between humans and machines, and potentially discover insights about cognition and collaboration that can set the foundation for a world where humans work with, as opposed to against, artificial intelligence to solve problems that neither human or artificial intelligence can solve on its own.
To better understand human-machine teamwork, it’s important to understand human-human teamwork (humans working together) and multi-agent systems (how artificial intelligence interacts as an agent that’s part of a group) to identify the characteristics that make humans and machines good teammates. This perspective lets us approach human-machine teamwork from the perspective of the human as well as the perspective of the machine. Thus, to reach a more accurate understanding of how humans and machines can work together, we examine human-machine teamwork through a series of studies.
In this dissertation, we conducted 4 studies and developed 2 theoretical models:
First, we focused on human-machine cooperation. We paired human participants with reinforcement learning agents to play two game
theory scenarios where individual interests and collective interests are in conflict to easily detect cooperation. We show that different reinforcement models exhibit different levels of cooperation, and that humans are more likely to cooperate if they believe they are playing with another human as opposed to a machine.
Second, we focused on human-machine coordination. We once again paired humans with machines to create a human-machine team to make them play a game
theory scenario that emphasizes convergence towards a mutually beneficial outcome. We also analyzed survey responses from the participants to highlight how many of the principles of human-human teamwork can still occur in human-machine teams even though communication is not possible.
Third, we reviewed the collective intelligence literature and the
prediction markets literature to develop a model for a
prediction market that enables humans and machines to work together to improve predictions. The model supports artificial intelligence operating as a peer in the
prediction market as well as a complementary aggregator.
Fourth, we reviewed the team cognition and collective intelligence literature to develop a model for teamwork that integrates team cognition, collective intelligence, and artificial intelligence. The model provides a new foundation to think about teamwork beyond the forecasting domain.
Next, we used a simulation of emergency response management to test the different teamwork aspects of a variety of human-machine teams compared to…
Advisors/Committee Members: Nathan McNeese, Brian Dean, Kelly Caine, Guo Freeman, Richard Pak.
Subjects/Keywords: collective intelligence; game theory; multi-agent systems; prediction markets; team cognition
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Canonico, L. B. (2019). Human-Machine Teamwork: An Exploration of Multi-Agent Systems, Team Cognition, and Collective Intelligence. (Doctoral Dissertation). Clemson University. Retrieved from https://tigerprints.clemson.edu/all_dissertations/2490
Chicago Manual of Style (16th Edition):
Canonico, Lorenzo Barberis. “Human-Machine Teamwork: An Exploration of Multi-Agent Systems, Team Cognition, and Collective Intelligence.” 2019. Doctoral Dissertation, Clemson University. Accessed January 23, 2021.
https://tigerprints.clemson.edu/all_dissertations/2490.
MLA Handbook (7th Edition):
Canonico, Lorenzo Barberis. “Human-Machine Teamwork: An Exploration of Multi-Agent Systems, Team Cognition, and Collective Intelligence.” 2019. Web. 23 Jan 2021.
Vancouver:
Canonico LB. Human-Machine Teamwork: An Exploration of Multi-Agent Systems, Team Cognition, and Collective Intelligence. [Internet] [Doctoral dissertation]. Clemson University; 2019. [cited 2021 Jan 23].
Available from: https://tigerprints.clemson.edu/all_dissertations/2490.
Council of Science Editors:
Canonico LB. Human-Machine Teamwork: An Exploration of Multi-Agent Systems, Team Cognition, and Collective Intelligence. [Doctoral Dissertation]. Clemson University; 2019. Available from: https://tigerprints.clemson.edu/all_dissertations/2490
Clemson University
21.
Mathieson, James.
Connective Complexity Methods for Analysis and Prediction in Engineering Design.
Degree: MS, Mechanical Engineering, 2011, Clemson University
URL: https://tigerprints.clemson.edu/all_theses/1085
► Complexity is an aspect of engineering design that is often addressed directly with the principle that 'designs should be simple'. However, such a principle…
(more)
▼ Complexity is an aspect of engineering design that is often addressed directly with the principle that 'designs should be simple'. However, such a principle fails to offer an effective means of quantifying the complexity of a given design for comparison and decision making. The measurement of complexity within a specific representations and domains has been well established. However, such measurements are inherently limited in their applicability and not always clear in their implications. This research presents a method of measuring complexity from different engineering representations in a consistent manner and explores the application of these measures. The development of a measurement method has suggested that complexity is the effort required to understand a given system and that this effort is based on a collection of attributes rather than a single value. These attributes are derived from graph-based representations and are divided into classes of size, interconnection, centrality, and decomposition. Each of these classes contains two measurement subtypes composed of multiple metrics each for a total of 29 dimensions of complexity. While this set is not exhaustive, it is considered to be sufficient for application. These complexity measurements are used in three application cases. The first of these cases applies complexity measurement to product connectivity graphs and establishes a model mapping these measurements to assembly time. The variability of the model are within one standard deviation of that observed between different designers conducting the same assembly time analysis. This demonstrates that it is possible to use complexity metrics as a surrogate mapping to design performance measures. The second application case addresses function structures and product market value. Complexity measurements are used as the input to neural networks to develop a mapping which gives a predicted probability density function over a range of market values. This mapping is shown to be accurate, while the precision is limited to the general product range due to a limited training set size. The success of this approach suggests that a formalized method to establishing complexity mappings can be established. The final application case develops a protocol for capturing the connective information in a design process. This protocol uses email, meeting minutes, and engineering documents to create a temporal hypergraph representation of the process. The application of complexity measurements to the data created by this protocol shows the ability to identify design process properties such as work habits, group dynamics, and critical points.
Advisors/Committee Members: Summers, Joshua D, Mocko , Gregory M, Goddard , Wayne D.
Subjects/Keywords: Complexity; Complexity Measurement; Graph Theory; Performance Prediction; Mechanical Engineering
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Mathieson, J. (2011). Connective Complexity Methods for Analysis and Prediction in Engineering Design. (Masters Thesis). Clemson University. Retrieved from https://tigerprints.clemson.edu/all_theses/1085
Chicago Manual of Style (16th Edition):
Mathieson, James. “Connective Complexity Methods for Analysis and Prediction in Engineering Design.” 2011. Masters Thesis, Clemson University. Accessed January 23, 2021.
https://tigerprints.clemson.edu/all_theses/1085.
MLA Handbook (7th Edition):
Mathieson, James. “Connective Complexity Methods for Analysis and Prediction in Engineering Design.” 2011. Web. 23 Jan 2021.
Vancouver:
Mathieson J. Connective Complexity Methods for Analysis and Prediction in Engineering Design. [Internet] [Masters thesis]. Clemson University; 2011. [cited 2021 Jan 23].
Available from: https://tigerprints.clemson.edu/all_theses/1085.
Council of Science Editors:
Mathieson J. Connective Complexity Methods for Analysis and Prediction in Engineering Design. [Masters Thesis]. Clemson University; 2011. Available from: https://tigerprints.clemson.edu/all_theses/1085
Georgia Tech
22.
Ferguson, David Edward.
The development of a self-adaptive prediction and control system.
Degree: MS, Industrial engineering, 1971, Georgia Tech
URL: http://hdl.handle.net/1853/30678
Subjects/Keywords: Time-series analysis; Prediction theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ferguson, D. E. (1971). The development of a self-adaptive prediction and control system. (Masters Thesis). Georgia Tech. Retrieved from http://hdl.handle.net/1853/30678
Chicago Manual of Style (16th Edition):
Ferguson, David Edward. “The development of a self-adaptive prediction and control system.” 1971. Masters Thesis, Georgia Tech. Accessed January 23, 2021.
http://hdl.handle.net/1853/30678.
MLA Handbook (7th Edition):
Ferguson, David Edward. “The development of a self-adaptive prediction and control system.” 1971. Web. 23 Jan 2021.
Vancouver:
Ferguson DE. The development of a self-adaptive prediction and control system. [Internet] [Masters thesis]. Georgia Tech; 1971. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/1853/30678.
Council of Science Editors:
Ferguson DE. The development of a self-adaptive prediction and control system. [Masters Thesis]. Georgia Tech; 1971. Available from: http://hdl.handle.net/1853/30678
University of Maryland
23.
London, Benjamin Alexei.
On the Stability of Structured Prediction.
Degree: Computer Science, 2015, University of Maryland
URL: http://hdl.handle.net/1903/17061
► Many important applications of artificial intelligence – such as image segmentation, part-of-speech tagging and network classification – are framed as multiple, interdependent prediction tasks. These structured prediction…
(more)
▼ Many important applications of artificial intelligence – such as image segmentation, part-of-speech tagging and network classification – are framed as multiple, interdependent
prediction tasks. These structured
prediction problems are typically modeled using some form of joint inference over the outputs, to exploit the relational dependencies. Joint reasoning can significantly improve predictive accuracy, but it introduces a complication in the analysis of structured models: the stability of inference. In optimizations involving multiple interdependent variables, such as joint inference, a small change to the input or parameters could induce drastic changes in the solution.
In this dissertation, I investigate the impact of stability in structured
prediction. I explore two topics, connected by the stability of inference. First, I provide generalization bounds for learning from a limited number of examples with large internal structure. The effective learning rate can be significantly sharper than rates given in related work. Under certain conditions on the data distribution and stability of the predictor, the bounds decrease with both the number of examples and the size of each example, meaning one could potentially learn from a single giant example. Secondly, I investigate the benefits of learning with strongly convex variational inference. Using the duality between strong convexity and stability, I demonstrate, both theoretically and empirically, that learning with a strongly convex free energy can result in significantly more accurate marginal probabilities. One consequence of this work is a new technique that ``strongly convexifies" many free energies used in practice. These two seemingly unrelated threads are tied by the idea that stable inference leads to lower error, particularly in the limited example setting, thereby demonstrating that inference stability is of critical importance to the study and practice of structured
prediction.
Advisors/Committee Members: Getoor, Lise (advisor).
Subjects/Keywords: Artificial intelligence; graphical models; machine learning; statistical learning theory; structured prediction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
London, B. A. (2015). On the Stability of Structured Prediction. (Thesis). University of Maryland. Retrieved from http://hdl.handle.net/1903/17061
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
London, Benjamin Alexei. “On the Stability of Structured Prediction.” 2015. Thesis, University of Maryland. Accessed January 23, 2021.
http://hdl.handle.net/1903/17061.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
London, Benjamin Alexei. “On the Stability of Structured Prediction.” 2015. Web. 23 Jan 2021.
Vancouver:
London BA. On the Stability of Structured Prediction. [Internet] [Thesis]. University of Maryland; 2015. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/1903/17061.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
London BA. On the Stability of Structured Prediction. [Thesis]. University of Maryland; 2015. Available from: http://hdl.handle.net/1903/17061
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Cambridge
24.
Nelson, Joseph Richard.
Crystal structure prediction at high pressures : stability, superconductivity and superionicity.
Degree: PhD, 2017, University of Cambridge
URL: https://doi.org/10.17863/CAM.14686
;
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744272
► The physical and chemical properties of materials are intimately related to their underlying crystal structure: the detailed arrangement of atoms and chemical bonds within. This…
(more)
▼ The physical and chemical properties of materials are intimately related to their underlying crystal structure: the detailed arrangement of atoms and chemical bonds within. This thesis uses computational methods to predict crystal structure, with a particular focus on structures and stable phases that emerge at high pressure. We explore three distinct systems. We first apply the ab initio random structure searching (AIRSS) technique and density functional theory (DFT) calculations to investigate the high-pressure behaviour of beryllium, magnesium and calcium difluorides. We find that beryllium fluoride is extensively polymorphic at low pressures, and predict two new phases for this compound - the silica moganite and CaCl2 structures - to be stable over the wide pressure range 12-57 GPa. For magnesium fluoride, our results show that the orthorhombic `O-I' TiO2 structure (Pbca, Z=8) is stable for this compound between 40 and 44 GPa. Our searches find no new phases at the static-lattice level for calcium difluoride between 0 and 70 GPa; however, a phase with P6̅2m symmetry is energetically close to stability over this pressure range, and our calculations predict that this phase is stabilised at high temperature. The P6̅2m structure exhibits an unstable phonon mode at large volumes which may signal a transition to a superionic state at high temperatures. The Group-II difluorides are isoelectronic to a number of other AB2-type compounds such as SiO2 and TiO2, and we discuss our results in light of these similarities. Compressed hydrogen sulfide (H2S) has recently attracted experimental and theoretical interest due to the observation of high-temperature superconductivity in this compound (Tc = 203 K) at high pressure (155 GPa). We use the AIRSS technique and DFT calculations to determine the stable phases and chemical stoichiometries formed in the hydrogen-sulfur system as a function of pressure. We find that this system supports numerous stable compounds: H3S, H7S3, H2S, H3S2, H4S3, H2S3 and HS2, at various pressures. Working as part of a collaboration, our predicted H3S and H4S3 structures are shown to be consistent with XRD data for this system, with H4S3 identified as a major decomposition product of H2S in the lead-up to the superconducting state. Calcium and oxygen are two elements of generally high terrestrial and cosmic abundance, and we explore structures of calcium peroxide (CaO2) in the pressure range 0-200 GPa. Stable structures for CaO2 with C2/c, I4/mcm and P21/c symmetries emerge at pressures below 40 GPa, which we find are thermodynamically stable against decomposition into CaO and O2. The stability of CaO2 with respect to decomposition increases with pressure, with peak stability occurring at the CaO B1-B2 phase transition at 65 GPa. Phonon calculations using the quasiharmonic approximation show that CaO2 is a stable oxide of calcium at mantle temperatures and pressures, highlighting a…
Subjects/Keywords: 571.6; Density functional theory; High-pressure physics; Crystal structure prediction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Nelson, J. R. (2017). Crystal structure prediction at high pressures : stability, superconductivity and superionicity. (Doctoral Dissertation). University of Cambridge. Retrieved from https://doi.org/10.17863/CAM.14686 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744272
Chicago Manual of Style (16th Edition):
Nelson, Joseph Richard. “Crystal structure prediction at high pressures : stability, superconductivity and superionicity.” 2017. Doctoral Dissertation, University of Cambridge. Accessed January 23, 2021.
https://doi.org/10.17863/CAM.14686 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744272.
MLA Handbook (7th Edition):
Nelson, Joseph Richard. “Crystal structure prediction at high pressures : stability, superconductivity and superionicity.” 2017. Web. 23 Jan 2021.
Vancouver:
Nelson JR. Crystal structure prediction at high pressures : stability, superconductivity and superionicity. [Internet] [Doctoral dissertation]. University of Cambridge; 2017. [cited 2021 Jan 23].
Available from: https://doi.org/10.17863/CAM.14686 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744272.
Council of Science Editors:
Nelson JR. Crystal structure prediction at high pressures : stability, superconductivity and superionicity. [Doctoral Dissertation]. University of Cambridge; 2017. Available from: https://doi.org/10.17863/CAM.14686 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744272
University of Cambridge
25.
Mayo, Martin.
Ab initio anode materials discovery for Li- and Na-ion batteries.
Degree: PhD, 2018, University of Cambridge
URL: https://doi.org/10.17863/CAM.17442
;
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744445
► This thesis uses first principles techniques, mainly the ab initio random structure searching method (AIRSS), to study anode materials for lithium- and sodium- ion batteries…
(more)
▼ This thesis uses first principles techniques, mainly the ab initio random structure searching method (AIRSS), to study anode materials for lithium- and sodium- ion batteries (LIBs and NIBs, respectively). Initial work relates to a theoretical structure prediction study of the lithium and sodium phosphide systems in the context of phosphorus anodes as candidates for LIBs and NIBs. The work reveals new Li-P and Na-P phases, some of which can be used to better interpret previous experimental results. By combining AIRSS searches with a high-throughput screening search from structures in the Inorganic Crystal Structure Database (ICSD), regions in the phase diagram are correlated to different ionic motifs and NMR chemical shielding is predicted from first principles. An electronic structure analysis of the Li-P and Na-P compounds is performed and its implication on the anode performance is discussed. The study is concluded by exploring the addition of aluminium dopants to the Li-P compounds to improve the electronic conductivity of the system. The following work deals with a study of tin anodes for NIBs. The structure prediction study yields a variety of new phases; of particular interest is a new NaSn2 phase predicted by AIRSS. This phase plays a crucial role in understanding the alloying mechanism of high-capacity tin anodes, work which was done in collaboration with experimental colleagues. Our predicted theoretical voltages give excellent agreement with the experimental electrochemical cycling curve. First principles molecular dynamics is used to propose an amorphous Na1Sn1 model which, in addition to the newly derived NaSn2 phase, provides help in revealing the electrochemical processes. In the subsequent work, we study Li-Sn and Li-Sb intermetallics in the context of alloy anodes for LIBs. A rich phase diagram of Li-Sn is present, exhibiting a variety of new phases. The calculated voltages show excellent agreement with previously reported cycling measurements and a consistent structural evolution of Li-Sn phases as Li concentration increases is revealed. The study concluded by calculating NMR parameters on the hexagonal- and cubic-Li3Sb phases which shed light on the interpretation of reported experimental data. We conclude with a structure prediction study of the pseudobinary Li-FeS2 system, where FeS2 is considered as a potential high-capacity electrochemical energy storage system. Our first principles calculations of intermediate structures help to elucidate the mechanism of charge storage observed by our experimental collaborators via it{in operando} studies.
Subjects/Keywords: 621.31; batteries; anodes; structure prediction; Density-functional theory; NMR; GIPAW
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Mayo, M. (2018). Ab initio anode materials discovery for Li- and Na-ion batteries. (Doctoral Dissertation). University of Cambridge. Retrieved from https://doi.org/10.17863/CAM.17442 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744445
Chicago Manual of Style (16th Edition):
Mayo, Martin. “Ab initio anode materials discovery for Li- and Na-ion batteries.” 2018. Doctoral Dissertation, University of Cambridge. Accessed January 23, 2021.
https://doi.org/10.17863/CAM.17442 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744445.
MLA Handbook (7th Edition):
Mayo, Martin. “Ab initio anode materials discovery for Li- and Na-ion batteries.” 2018. Web. 23 Jan 2021.
Vancouver:
Mayo M. Ab initio anode materials discovery for Li- and Na-ion batteries. [Internet] [Doctoral dissertation]. University of Cambridge; 2018. [cited 2021 Jan 23].
Available from: https://doi.org/10.17863/CAM.17442 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744445.
Council of Science Editors:
Mayo M. Ab initio anode materials discovery for Li- and Na-ion batteries. [Doctoral Dissertation]. University of Cambridge; 2018. Available from: https://doi.org/10.17863/CAM.17442 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.744445
University of British Columbia
26.
Campbell, Alyce.
An empirical study of a financial signalling model.
Degree: PhD, Business Administration, 1987, University of British Columbia
URL: http://hdl.handle.net/2429/26969
► Brennan and Kraus (1982,1986) developed a costless signalling model which can explain why managers issue hybrid securities—convertibles(CB's) or bond-warrant packages(BW's). The model predicts that when…
(more)
▼ Brennan and Kraus (1982,1986) developed a costless signalling model which can explain why managers issue hybrid securities—convertibles(CB's) or bond-warrant packages(BW's). The model predicts that when the true standard deviation (σ) of the distribution of future firm value is unknown to the market, the firm's managers will issue a hybrid with specific characteristics such that the security's full information value is at a minimum at the firm's true σ. In this fully revealing equilibrium market price is equal to this minimum value.
In this study, first the mathematical properties of the hypothesized bond-valuation model were examined to see if specific functions could have a minimum not at σ = 0 or σ = ∞ as required for signalling. The Black-Scholes-Merton model was the valuation model chosen because of ease of use, supporting empirical evidence, and compatibility with the Brennan-Kraus model. Three different variations, developed from Ingersoll(1977a); Geske( 1977,1979) and Geske and Johnson(1984); and Brennan and Schwartz(1977,1978), were examined. For all hybrids except senior CB's, pricing functions with a minimum can be found for plausible input parameters. However, functions with an interior maximum are also plausible. A function with a maximum cannot be used for signalling.
Second, bond pricing functions for 105 hybrids were studied. The two main hypotheses were: (1) most hybrids have functions with an interior minimum; (2) market price equals minimum theoretical value. The results do not support the signalling model, although the evidence is ambiguous. For the σ range 0.05-0.70, for CB's (BW's) 15(8) Brennan-Schwartz functions were everywhere positively sloping, 11(2) had an interior minimum, 22(0) were everywhere negatively sloping, and 35(12) had an interior maximum. Market prices did lie closer to minima than maxima from the Brennan-Schwartz solutions, but the results suggest that the solution as implemented overpriced the CB's. BW's were unambiguously overpriced. With consistent overpricing, market prices would naturally lie closer to minima. Average variation in theoretical values was, however, only about 5 percent for CB's and about 10 percent for BW's. This, coupled with the shape data, suggests that firms were choosing securities with theoretical values relatively insensitive to a rather than choosing securities to signal σ unambiguously.
Subjects/Keywords: Prediction theory; Finance – Mathematical models
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Campbell, A. (1987). An empirical study of a financial signalling model. (Doctoral Dissertation). University of British Columbia. Retrieved from http://hdl.handle.net/2429/26969
Chicago Manual of Style (16th Edition):
Campbell, Alyce. “An empirical study of a financial signalling model.” 1987. Doctoral Dissertation, University of British Columbia. Accessed January 23, 2021.
http://hdl.handle.net/2429/26969.
MLA Handbook (7th Edition):
Campbell, Alyce. “An empirical study of a financial signalling model.” 1987. Web. 23 Jan 2021.
Vancouver:
Campbell A. An empirical study of a financial signalling model. [Internet] [Doctoral dissertation]. University of British Columbia; 1987. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/2429/26969.
Council of Science Editors:
Campbell A. An empirical study of a financial signalling model. [Doctoral Dissertation]. University of British Columbia; 1987. Available from: http://hdl.handle.net/2429/26969
University of Cambridge
27.
Burghi, Thiago.
Feedback for neuronal system identification.
Degree: PhD, 2019, University of Cambridge
URL: https://doi.org/10.17863/CAM.57543
;
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814503
► In order to estimate reliable models from noisy input-output data, system identification techniques usually require that the data be generated by a process with a…
(more)
▼ In order to estimate reliable models from noisy input-output data, system identification techniques usually require that the data be generated by a process with a fading memory. Non-equilibrium systems such as neuronal and chaotic models lack a fading memory. Their identification is challenging, in particular in the presence of input noise. In this thesis, we propose a methodology based on the prediction-error method for the identification of neuronal systems subject to input-additive noise. We build on the fundamental observation that while a neuronal model does not have a fading memory, it can be transformed into a fading memory system by output feedback. Our ideas can be generalized to any non-equilibrium system sharing this property. At the core of the methodology is the use of output feedback in experiment design. We provide a theoretical justification for this design choice, which has been exploited in neurophysiology since the invention of the voltage-clamp experiment. To investigate the problem of feedback for identification, we first address the estimation of simple non-equilibrium systems in Lure form, and show that feedback allows estimating the nonlinearity in a static experiment. We then address the estimation of conductance-based models. Assuming that an informed choice can be made on the elements of the model structure, we show that consistent parameter estimates can be obtained when noise is only present at the system input. Finally, we approach the problem from a black-box perspective, and propose identifying the neuronal internal dynamics using a universal approximator with Generalized Orthogonal Basis Functions.
Subjects/Keywords: System identification; Prediction error method; Contraction theory; Fading memory; Electrophysiology; Neuroscience
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Burghi, T. (2019). Feedback for neuronal system identification. (Doctoral Dissertation). University of Cambridge. Retrieved from https://doi.org/10.17863/CAM.57543 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814503
Chicago Manual of Style (16th Edition):
Burghi, Thiago. “Feedback for neuronal system identification.” 2019. Doctoral Dissertation, University of Cambridge. Accessed January 23, 2021.
https://doi.org/10.17863/CAM.57543 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814503.
MLA Handbook (7th Edition):
Burghi, Thiago. “Feedback for neuronal system identification.” 2019. Web. 23 Jan 2021.
Vancouver:
Burghi T. Feedback for neuronal system identification. [Internet] [Doctoral dissertation]. University of Cambridge; 2019. [cited 2021 Jan 23].
Available from: https://doi.org/10.17863/CAM.57543 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814503.
Council of Science Editors:
Burghi T. Feedback for neuronal system identification. [Doctoral Dissertation]. University of Cambridge; 2019. Available from: https://doi.org/10.17863/CAM.57543 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.814503
University of British Columbia
28.
Freeland, R. Keith.
Statistical analysis of discrete time series with application to the analysis of workers' compensation claims data.
Degree: PhD, Business Administration, 1998, University of British Columbia
URL: http://hdl.handle.net/2429/8500
► This thesis examines the statistical properties of the Poisson AR(1) model of Al-Osh and Alzaid (1987) and McKenzie (1988). The analysis includes forecasting, estimation, testing…
(more)
▼ This thesis examines the statistical properties of the Poisson AR(1) model of Al-Osh and Alzaid (1987) and McKenzie (1988). The analysis includes forecasting,
estimation, testing for independence and specification and the addition of regressors to
the model.
The Poisson AR(1) model is an infinite server queue, and as such is well suited
for modeling short-term disability claimants who are waiting to recover from an injury or
illness. One of the goals of the thesis is to develop statistical methods for analyzing series
of monthly counts of claimants collecting short-term disability benefits from the
Workers' Compensation Board (WCB) of British Columbia.
We consider four types of forecasts, which are the k-step ahead conditional mean,
median, mode and distribution. For low count series the k-step ahead conditional
distribution is practical and much more informative than the other forecasts.
We consider three estimation methods: conditional least squares (CLS),
generalized least squares (GLS) and maximum likelihood (ML). In the case of CLS
estimation we find an analytic expression for the information and in the GLS case we find
an approximation for the information. We find neat expressions for the score function and
the observed Fisher information matrix. The score expressions leads to new definitions of
residuals.
Special care is taken to test for independence since the test is on the boundary of
the parameter space. The score test is asymptotically equivalent to testing whether the
CLS estimate of the correlation coefficient is zero. Further we define a Wald and
likelihood ratio test.
Then we use the general specification test of McCabe and Leybourne (1996) to
test whether the model is sufficient to explain the variation found in the data.
Next we add regressors to the model and update our earlier forecasting, estimation
and testing results. We also show the model is identifiable.
We conclude with a detailed application to monthly WCB claims counts. The
preliminary analysis includes plots of the series, autocorrelation function and partial
autocorrelation function. Model selection is based on the preliminary analysis, t-tests for
the parameters, the general specification test and residuals. We also include forecasts for
the first six months of 1995.
Subjects/Keywords: Time-series analysis.; Prediction theory.
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Freeland, R. K. (1998). Statistical analysis of discrete time series with application to the analysis of workers' compensation claims data. (Doctoral Dissertation). University of British Columbia. Retrieved from http://hdl.handle.net/2429/8500
Chicago Manual of Style (16th Edition):
Freeland, R Keith. “Statistical analysis of discrete time series with application to the analysis of workers' compensation claims data.” 1998. Doctoral Dissertation, University of British Columbia. Accessed January 23, 2021.
http://hdl.handle.net/2429/8500.
MLA Handbook (7th Edition):
Freeland, R Keith. “Statistical analysis of discrete time series with application to the analysis of workers' compensation claims data.” 1998. Web. 23 Jan 2021.
Vancouver:
Freeland RK. Statistical analysis of discrete time series with application to the analysis of workers' compensation claims data. [Internet] [Doctoral dissertation]. University of British Columbia; 1998. [cited 2021 Jan 23].
Available from: http://hdl.handle.net/2429/8500.
Council of Science Editors:
Freeland RK. Statistical analysis of discrete time series with application to the analysis of workers' compensation claims data. [Doctoral Dissertation]. University of British Columbia; 1998. Available from: http://hdl.handle.net/2429/8500
Michigan State University
29.
Sorensen, Roy A.
Moore's problem and the prediction paradox : new limits for epistemology.
Degree: PhD, Department of Philosophy, 1982, Michigan State University
URL: http://etd.lib.msu.edu/islandora/object/etd:37078
Subjects/Keywords: Knowledge, Theory of; Prediction (Logic)
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Sorensen, R. A. (1982). Moore's problem and the prediction paradox : new limits for epistemology. (Doctoral Dissertation). Michigan State University. Retrieved from http://etd.lib.msu.edu/islandora/object/etd:37078
Chicago Manual of Style (16th Edition):
Sorensen, Roy A. “Moore's problem and the prediction paradox : new limits for epistemology.” 1982. Doctoral Dissertation, Michigan State University. Accessed January 23, 2021.
http://etd.lib.msu.edu/islandora/object/etd:37078.
MLA Handbook (7th Edition):
Sorensen, Roy A. “Moore's problem and the prediction paradox : new limits for epistemology.” 1982. Web. 23 Jan 2021.
Vancouver:
Sorensen RA. Moore's problem and the prediction paradox : new limits for epistemology. [Internet] [Doctoral dissertation]. Michigan State University; 1982. [cited 2021 Jan 23].
Available from: http://etd.lib.msu.edu/islandora/object/etd:37078.
Council of Science Editors:
Sorensen RA. Moore's problem and the prediction paradox : new limits for epistemology. [Doctoral Dissertation]. Michigan State University; 1982. Available from: http://etd.lib.msu.edu/islandora/object/etd:37078
University of Cambridge
30.
Burghi, Thiago.
Feedback for neuronal system identification.
Degree: PhD, 2019, University of Cambridge
URL: https://www.repository.cam.ac.uk/handle/1810/310449
► In order to estimate reliable models from noisy input-output data, system identification techniques usually require that the data be generated by a process with a…
(more)
▼ In order to estimate reliable models from noisy input-output data, system identification techniques usually require that the data be generated by a process with a fading memory. Non-equilibrium systems such as neuronal and chaotic models lack a fading memory. Their identification is challenging, in particular in the presence of input noise. In this thesis, we propose a methodology based on the prediction-error method for the identification of neuronal systems subject to input-additive noise. We build on the fundamental observation that while a neuronal model does not have a fading memory, it can be transformed into a fading memory system by output feedback. Our ideas can be generalized to any non-equilibrium system sharing this property. At the core of the methodology is the use of output feedback in experiment design. We provide a theoretical justification for this design choice, which has been exploited in neurophysiology since the invention of the voltage-clamp experiment. To investigate the problem of feedback for identification, we first address the estimation of simple non-equilibrium systems in Lure form, and show that feedback allows estimating the nonlinearity in a static experiment. We then address the estimation of conductance-based models. Assuming that an informed choice can be made on the elements of the model structure, we show that consistent parameter estimates can be obtained when noise is only present at the system input. Finally, we approach the problem from a black-box perspective, and propose identifying the neuronal internal dynamics using a universal approximator with Generalized Orthogonal Basis Functions.
Subjects/Keywords: System identification; Prediction error method; Contraction theory; Fading memory; Electrophysiology; Neuroscience
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Burghi, T. (2019). Feedback for neuronal system identification. (Doctoral Dissertation). University of Cambridge. Retrieved from https://www.repository.cam.ac.uk/handle/1810/310449
Chicago Manual of Style (16th Edition):
Burghi, Thiago. “Feedback for neuronal system identification.” 2019. Doctoral Dissertation, University of Cambridge. Accessed January 23, 2021.
https://www.repository.cam.ac.uk/handle/1810/310449.
MLA Handbook (7th Edition):
Burghi, Thiago. “Feedback for neuronal system identification.” 2019. Web. 23 Jan 2021.
Vancouver:
Burghi T. Feedback for neuronal system identification. [Internet] [Doctoral dissertation]. University of Cambridge; 2019. [cited 2021 Jan 23].
Available from: https://www.repository.cam.ac.uk/handle/1810/310449.
Council of Science Editors:
Burghi T. Feedback for neuronal system identification. [Doctoral Dissertation]. University of Cambridge; 2019. Available from: https://www.repository.cam.ac.uk/handle/1810/310449
◁ [1] [2] [3] [4] [5] [6] [7] [8] ▶
. 
Open Access Theses and Dissertations
