Chow, Chi Wang. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2013. / Includes bibliographical references (leaves [81]-84). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web.

Thesis (Ph.D.)--University of Delaware, 2009. / Principal faculty advisor: John Case, Dept. of Computer & Information Sciences. Includes bibliographical references.

Thesis (M.S.)--Montana State University--Bozeman, 2007. / Typescript. Chairperson, Graduate Committee: Rockford J. Ross. Includes bibliographical references (leaves 55-56).

Darwin's theory (1859) proposes that evolution progresses by the survival of those individuals in the population that have greater fitness. Modern understanding of Darwinian evolution is that variation in phenotype, or functional behavior, is caused by variation in genotype, or the DNA sequence. However, a quantitative understanding of what functional behaviors may emerge through Darwinian mechanisms, within reasonable computational and information-theoretic resources, has not been established. Valiant (2006) proposed a computational model to address the question of the complexity of functions that may be evolved through Darwinian mechanisms. In Valiant's model, the goal is to evolve a representation that computes a function that is close to some ideal function under the target distribution. While this evolution model can be simulated in the statistical query learning framework of Kearns (1993), Feldman has shown that under some constraints the reverse also holds, in the sense that learning algorithms in this framework may be cast as evolutionary mechanisms in Valiant's model. In this thesis, we present three results in Valiant's computational model of evolution. The first shows that evolutionary mechanisms in this model can be made robust to gradual drift in the ideal function, and that such drift resistance is universal, in the sense that, if some concept class is evolvable when the ideal function is stationary, it is also evolvable in the setting when the ideal function drifts at some low rate. The second result shows that under certain de nitions of recombination and for certain selection mechanisms, evolution with recombination may be substantially faster. We show that in many cases polylogarithmic, rather than polynomial, generations are sufficient to evolve a concept class, whenever a suitable parallel learning algorithm exists. The third result shows that computation, and not just information, is a limiting resource for evolution. We show that when computational resources in Valiant's model are allowed to be unbounded, while requiring that the information-theoretic resources be polynomially bounded, more concept classes are evolvable. This result is based on widely believed conjectures from complexity theory. / Engineering and Applied Sciences

Both the learning model and the learning process of CSPL are customized to different query instances. CSPL can make use of the characteristics of the query instance to explore a focused hypothesis space effectively during classification. Unlike many existing learning methods, CSPL conducts learning from specific to general, effectively avoiding the horizon effect. Empirical investigation demonstrates that learning from specific to general can discover more useful patterns for learning. Experimental results on benchmark data sets and real-world problems demonstrate that our CSPL framework has a prominent learning performance in comparison with existing learning rnethods. / CSPL integrates the attributes and instances in a query matrix model under customized learning framework. Within this query matrix model, it can be demonstrated that attributes and instances have a useful symmetry property for learning. This symmetry property leads to a solution for counteracting the negative factor of sparse instances with the abundance of attribute information, which was previously viewed as a kind of dimension curse for common learning methods. Given this symmetry property, we propose to use support patterns as the basic learning unit of CSPL, i.e., the patterns to be explored. Generally, a support pattern can be viewed as a sub-matrix of the query matrix, considering its associated support instances and attribute values. CSPL discovers useful support patterns and combines their statistics for classifying unseen instances. / The developing of machine learning techniques still has a number of challenges. Real world problems often require a more flexible and dynamic learning method, which is customized to the learning scenario and user demand. For example, it is quite often in real-world applications to make a critical decision with only limited data but huge amount of potentially relevant attributes. Therefore, we propose a novel customized learning framework called Customized Support Pattern Learner (CSPL), which exploits a tradeoff between instance-based learning and attribute-based learning. / Han Yiqiu. / "October 2005." / Adviser: Wai Lam. / Source: Dissertation Abstracts International, Volume: 67-07, Section: B, page: 3898. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (p. 99-104). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract in English and Chinese. / School code: 1307.

Huang Kaizhu. / "July 2004." / Thesis (Ph.D.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (p. 176-194) / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Mode of access: World Wide Web. / Abstracts in English and Chinese.

A classical algorithm in classification is the support vector machine (SVM) algorithm. Based on Vapnik's statistical learning theory, it tries to find a linear boundary with maximum margin to separate the given data into different classes. In non-separable case, SVM uses a kernel trick to map the data onto a feature space and finds a linear boundary in the new space. / Different algorithms are derived from the framework. When the empirical error is defined by a quadratic loss, we have generalized regularized least-squares learning algorithm. When the idea is applied to SVM, we obtain semi-parametric SVM algorithm. Besides, we derive the third algorithm which generalizes the kernel logistic regression algorithm. / How to choose non-regularized features? We give some empirical studies. We use dimensionality reduction techniques in text categorization, extract some non-regularized intrinsic features for the high dimensional data, and report improved results. / Instead of understanding SVM's behavior from Vapnik's theory, our work follows regularized learning viewpoint. In regularized learning, people try to find a solution from a function space which has small empirical error in explaining the input-output relationship for training data, yet keeping the simplicity of the solution. / To provide the simplicity, the complexity of the solution is penalized, which involves all features in the function space. An equal penalty, as in standard regularized learning, is reasonable without knowing the significance of individual features. But how about if we have prior knowledge that some features are more important than others? Instead of penalizing all features, we study a generalized regularized learning framework where part of the function space is not penalized, and derive its corresponding solution. / Two generalized algorithms need to solve positive definite linear systems to get the parameters. How to solve a large-scale linear system efficiently? Different from previous work in machine learning where people generally resort to conjugate gradient method, our work proposes to use a domain decomposition approach. New interpretations and improved results are reported accordingly. / Li, Wenye. / "September 2007." / Advisers: Kwong-Sak Leung; Kin-Hong Lee. / Source: Dissertation Abstracts International, Volume: 69-08, Section: B, page: 4850. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (p. 101-109). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts in English and Chinese. / School code: 1307.

Thesis (Ph.D.)--City University of Hong Kong, 2009. / "Submitted to Department of Mathematics in partial fulfillment of the requirements for the degree of Doctor of Philosophy." Includes bibliographical references (leaves [87]-100)

Thesis (Ph.D)--Computing, Georgia Institute of Technology, 2009. / Committee Chair: Khot, Subhash; Committee Member: Tetali, Prasad; Committee Member: Thomas, Robin; Committee Member: Vempala, Santosh; Committee Member: Vigoda, Eric. Part of the SMARTech Electronic Thesis and Dissertation Collection.

Thesis (Ph.D)--Industrial and Systems Engineering, Georgia Institute of Technology, 2009. / Committee Chair: Wu, C. F. Jeff; Committee Co-Chair: Yuan, Ming; Committee Member: Huo, Xiaoming; Committee Member: Vengazhiyil, Roshan Joseph; Committee Member: Wang, Zhonglin. Part of the SMARTech Electronic Thesis and Dissertation Collection.