Thesis (M.A.)--Florida State University, 2003. / Advisor: Dr. Laura Edmonson [sic], Florida State University, School of Theatre. Title and description from dissertation home page (viewed Oct. 1, 2003). Includes bibliographical references.

Thesis (M.A.)--Ohio state University. / Ohio state university studies. Bibliography: p. 41-43.

Thesis (Ph. D.)--University of Texas at Austin, 2002. / Vita. Includes bibliographical references (leaves 175-180). Available also in a digital version from Dissertation Abstracts.

Thesis (M.S.)--California Polytechnic State University, 2010. / Title from PDF title page; viewed on February 22, 2010. Major professor: Xiao-Hua (Helen) Yu, Ph.D. "Presented to the faculty of California Polytechnic State University, San Luis Obispo." "In partial fulfillment of the requirements for the degree [of] Master of Science in Electrical Engineering." "February, 2010." Includes bibliographical references (p. 90-91).

Thesis (M.A. in International Security and Civil-Military Relations)--Naval Postgraduate School, June 2003. / Thesis advisor(s): Donald Abenheim, Robert Looney. Includes bibliographical references. Also available online.

The problem of multiagent learning (or MAL) is concerned with the study of how agents can learn and adapt in the presence of other agents that are simultaneously adapting. The problem is often studied in the stylized settings provided by repeated matrix games. The goal of this thesis is to develop MAL algorithms for such a setting that achieve a new set of objectives which have not been previously achieved. The thesis makes three main contributions. The first main contribution proposes a novel MAL algorithm, called Convergence with Model Learning and Safety (or CMLeS), that is the first to achieve the following three objectives: (1) converges to following a Nash equilibrium joint-policy in self-play; (2) achieves close to the best response when interacting with a set of memory-bounded agents whose memory size is upper bounded by a known value; and (3) ensures an individual return that is very close to its security value when interacting with any other set of agents. The second main contribution proposes another novel MAL algorithm that models a significantly more complex class of agent behavior called Markovian agents, that subsumes the class of memory-bounded agents. Called Joint Optimization against Markovian Agents (or Joma), it achieves the following two objectives: (1) achieves a joint-return very close to the social welfare maximizing joint-return when interacting with Markovian agents; (2) ensures an individual return that is very close to its security value when interacting with any other set of agents. Finally, the third main contribution shows how a key subroutine of Joma can be extended to solve a broader class of problems pertaining to Reinforcement Learning, called ``Structure Learning in factored state MDPs". All of the algorithms presented in this thesis are well backed with rigorous theoretical analysis, including an analysis on sample complexity wherever applicable, as well as representative empirical tests. / text

Executive functioning abilities, including abstract reasoning, are often reported as weaknesses in autism spectrum disorders (ASDs). The current study examines reasoning through a different approach by utilizing the Cattell-Horn-Carroll (CHC) theory of intelligence, which is a widely accepted, research-based model that defines reasoning or fluid intelligence (Gf) and outlines those smaller skills of which it is composed. The Woodcock-Johnson, Third Edition (WJ III) is a test battery based on CHC theory, assessing the broad and narrow abilities of the model. Young men with high-functioning autism spectrum disorders (HFASDs) and neurotypical controls were given the WJ III tasks that assess the four narrow abilities of fluid intelligence - general sequential reasoning/deductive reasoning (RG), induction/inductive reasoning (I), speed of reasoning (RE), and quantitative reasoning/math reasoning (RQ). It was hypothesized that while deductive reasoning, inductive reasoning, and reasoning speed would be lower for HFASD, math reasoning would be comparable between groups. This expectation was based on previous autism research, which has found reasoning and processing speed deficits but preserved math skills. The present study also sought to examine cerebellar volume, through structural brain imaging, and its relationship to reasoning abilities. The HFASD group was expected to have reduced cerebellar volume when compared to controls. The ASD literature contains many examples of this pattern of brain structure, with the cerebellum being the most commonly cited region of abnormality. Additionally, the cerebellum has been implicated in studies of executive functioning, and a relationship between size and performance on nonverbal reasoning tasks has been reported. Therefore, a positive correlation was hypothesized between cerebellar volume and scores on WJ III reasoning tasks. Twenty-one young adult male HFASD subjects and 21 neurotypical controls were included in the current study. The data was analyzed through the use of MANOVA/MANCOVA, t-tests, and Pearson correlations. Results supported fluid intelligence weaknesses in the HFASD sample, with significantly lower performance in speed of reasoning. Deductive and inductive reasoning abilities were also lower, though these findings did not reach significance. The data did not support decreased cerebellar volume in HFASD, nor was a relationship between fluid reasoning and volume of the cerebellum found. / text

Intelligent organisms do not simply perform one task, but exhibit multiple distinct modes of behavior. For instance, humans can swim, climb, write, solve problems, and play sports. To be fully autonomous and robust, it would be advantageous for artificial agents, both in physical and virtual worlds, to exhibit a similar diversity of behaviors. This dissertation develops methods for discovering such behavior automatically using multiobjective neuroevolution. First, sensors are designed to allow multiple different interpretations of objects in the environment (such as predator or prey). Second, evolving networks are given ways of representing multiple policies explicitly via modular architectures. Third, the set of objectives is dynamically adjusted in order to lead the population towards the most promising areas of the search space. These methods are evaluated in five domains that provide examples of three different types of task divisions. Isolated tasks are separate from each other, but a single agent must solve each of them. Interleaved tasks are distinct, but switch back and forth within a single evaluation. Blended tasks do not have clear barriers, because an agent may have to perform multiple behaviors at the same time, or learn when to switch between opposing behaviors. The most challenging of the domains is Ms. Pac-Man, a popular classic arcade game with blended tasks. Methods for developing multimodal behavior are shown to achieve scores superior to other Ms. Pac-Man results previously published in the literature. These results demonstrate that complex multimodal behavior can be evolved automatically, resulting in robust and intelligent agents. / text

Not available / text

Artificial Neural Networks (ANNs) have been developed for many applications but no detailed study has been made in the measure of their quality such as efficiency and complexity using appropriate metrics. Without an appropriate measurement, it is difficult to tell how an ANN performs on given applications. In addition, it is difficult to provide a measure of the algorithmic complexity of any given application. Further, it is difficult to make use of the results obtained in an application to predict the ANN's quality in a similar application. This research was undertaken to develop metrics, named Neural Metrics, that can be used in the measurement, construction and specification of backpropagation based supervised feedforward ANNs for applied science and engineering applications. A detailed analysis of backpropagation was carried out with a view to studying the mathematical definitions of the proposed metrics. Variants of backpropagation using various optimisation techniques were evaluated with similar computational and metric analysis. The research involved the evaluation of the proposed set of neural metrics using the computer implementation of training algorithms across a number of scientific and engineering benchmark problems including binary and real type training data. The result of the evaluation, for each type of problem, was a specification of values for all neural metrics and network parameters that can be used to successfully solve the same type of problem. With such a specification, neural users can reduce the uncertainty and hence time in choosing the appropriate network details for solving the same type of problem. It is also possible to use the specified neural metric values as reference points to further the experiments with a view to obtaining a better or sub-optimal solution for the problem. In addition, the generalised results obtained in this study provide users not only with a better understanding of the algorithmic complexity of the problem but also with a useful guideline on predicting the values of metrics that are normally determined empirically. It must be emphasised that this study only considers metrics for assessment of construction and off-line training of neural networks. The operational performance (e.g. on-line deployment of the trained networks) is outside the scope. Operational results (e.g. CPU time and run time errors) on training the networks off-line were obtained and discussed for each type of application problem.