Thesis (Ph.D.)--McMaster University, 2005. / Supervisors: M.A. Elbestawi, G.M. Bone. Includes bibliographical references (leaves 117-122).

Thesis (Ph. D.)--Washington State University, December 2007. / Includes bibliographical references (p. 98-107).

No description available.

La recherche en Interaction Homme-Machine a produit de nombreuses techniques d'interaction pour améliorer l'utilisabilité des applications graphiques alors que les produits industriels n'en tirent que très rarement profit. Ce constat est dû à un manque d'outils pour faire des choix informés et mettre en oeuvre ces choix. Cette thèse propose trois outils utilisables en synergie pour favoriser l'adoption de techniques d'interaction avancées, depuis l'imagination d'une technique jusqu'à son implémentation. Le premier outil, Complexity of Interaction Sequences (CIS), est un modèle pour décrire une technique d'interaction et prédire son efficacité dans un contexte d'utilisation donné. Le niveau d'abstraction élevé de CIS en fait un outil utilisable en amont de la conception et de l'évaluation afin de pouvoir envisager plusieurs techniques et apprécier leur efficacité à moindre coût. Le second outil, Touchstone, est une plateforme pour aider à la conception d'expérimentations contrôlées. Son aspect exploratoire et son architecture modulaire permettent la réutilisation et facilitent la réalisation d'expérimentations contrôlées. Touchstone est non seulement destinée aux évaluateurs, mais également aux concepteurs grâce à sa fonction d'entrepôt de résultats empiriques. Enfin, SwingStates est une boîte à outils qui introduit un modèle de dessin et des structures de contrôle adaptées à la programmation de techniques d'interaction avancées. SwingStates est une extension de Java Swing, une boîte à outils largement utilisée pour le développement d'interfaces graphiques, et offre ainsi de nouvelles possibilités au développeur tout en restant dans leur cadre de travail habituel.

Reinforcement Learning (RL) is the study of agents that learn optimal behavior by interacting with and receiving rewards and punishments from an unknown environment. RL agents typically do this by learning value functions that assign a value to each state (situation) or to each state-action pair. Recently, there has been a growing interest in using hierarchical methods to cope with the complexity that arises due to the huge number of states found in most interesting real-world problems. Hierarchical methods seek to reduce this complexity by the use of temporal and state abstraction. Like most RL methods, most hierarchical RL methods optimize the discounted total reward that the agent receives. However, in many domains, the proper criteria to optimize is the average reward per time step. In this thesis, we adapt the concepts of hierarchical and recursive optimality, which are used to describe the kind of optimality achieved by hierarchical methods, to the average reward setting and show that they coincide under a condition called Result Distribution Invariance. We present two new model-based hierarchical RL methods, HH-learning and HAH-learning, that are intended to optimize the average reward. HH-learning is a hierarchical extension of the model-based, average-reward RL method, H-learning. Like H-learning, HH-learning requires exploration in order to learn correct domain models and optimal value function. HH-learning can be used with any exploration strategy whereas HAH-learning uses the principle of "optimism under uncertainty", which gives it a built-in "auto-exploratory" feature. We also give the hierarchical and auto-exploratory hierarchical versions of R-learning, a model-free average reward method, and a hierarchical version of ARTDP, a model-based discounted total reward method. We compare the performance of the "flat" and hierarchical methods in the task of scheduling an Automated Guided Vehicle (AGV) in a variety of settings. The results show that hierarchical methods can take advantage of temporal and state abstraction and converge in fewer steps than the flat methods. The exception is the hierarchical version of ARTDP. We give an explanation for this anomaly. Auto-exploratory hierarchical methods are faster than the hierarchical methods with ��-greedy exploration. Finally, hierarchical model-based methods are faster than hierarchical model-free methods. / Graduation date: 2003

"May 27, 1959." / Bibliography: p. 12. / Army Signal Corps Contract No. DA36-039-sc-78108. Dept. of the Army Project 3-99-00-100.

This thesis examines a complete design framework for a real-time, autonomous system with specialized VLSI hardware for computing 3-D camera motion. In the proposed architecture, the first step is to determine point correspondences between two images. Two processors, a CCD array edge detector and a mixed analog/digital binary block correlator, are proposed for this task. The report is divided into three parts. Part I covers the algorithmic analysis; part II describes the design and test of a 32$\time $32 CCD edge detector fabricated through MOSIS; and part III compares the design of the mixed analog/digital correlator to a fully digital implementation.

Radiotherapy is often used to treat prostate cancer. While using high dose of radiation does kill cancer cells, it can cause toxicity in healthy tissues for some patients. It would be best to apply this treatment only to patients who are likely to be immune from such toxicity. This requires a classifier that can predict, before treatment, which patients are likely to exhibit severe toxicity. Here, we explore ways to use certain genetic features, called Single Nucleotide Polymorphisms (SNPs), for this task. This thesis uses several machine learning methods for learning such classifiers for predicting toxicity. This problem is challenging as there are a large number of features (164,273 SNPs) but only 82 samples. We explore an ensemble classification method for this problem, called Mixture Using Variance (MUV), which first learns several different base probabilistic classifiers, then for each query combines the responses of the different base classifiers based on their respective variances. The original MUV learns the individual classifiers using bootstrap sampling of the training data; we modify this by considering different subsets of the features for each classifier. We derive a new combination rule for base classifiers in the proposed setting and obtain some new theoretical results. Based on characteristics of our task, we propose an approach that involves first clustering the features before selecting only a subset of features from each cluster for each base classifier. Unfortunately, we were unable to predict radiation toxicity in prostate cancer patients using just the SNP values. However, our further experimental results reveal strong relation between correctness of a classifier in its prediction and the variance of the response to the corresponding classification query, which show that the main idea is promising.

Developing logic in machines has always been an area of concern for scientists. Automated Theorem Proving is a field that has implemented the concept of logical consequence to a certain level. However, if the number of available axioms is very large then the probability of getting a proof for a conjecture in a reasonable time limit can be very small. This is where the ability to learn from previously proved theorems comes into play. If we see in our own lives, whenever a new situation S(NEW) is encountered we try to recollect all old scenarios S(OLD) in our neural system similar to the new one. Based on them we then try to find a solution for S(NEW) with the help of all related facts F(OLD) to S(OLD). Similar is the concept in this research. The thesis deals with developing a solution and finally implementing it in a tool that tries to prove a failed conjecture (a problem that the ATP system failed to prove) by extracting a sufficient set of axioms (we call it Refined Axiom Set (RAS)) from a large pool of available axioms. The process is carried out by measuring the similarity of a failed conjecture with solved theorems (already proved) of the same domain. We call it "process1", which is based on syntactic selection of axioms. After process1, RAS may still have irrelevant axioms, which motivated us to apply semantic selection approach on RAS so as to refine it to a much finer level. We call this approach as "process2". We then try to prove failed conjecture either from the output of process1 or process2, depending upon whichever approach is selected by the user. As for our testing result domain, we picked all FOF problems from the TPTP problem domain called SWC, which consisted of 24 broken conjectures (problems for which the ATP system is able to show that proof exists but not able to find it because of limited resources), 124 failed conjectures and 274 solved theorems. The results are produced by keeping in account both the broken and failed problems. The percentage of broken conjectures being solved with respect to the failed conjectures is obviously higher and the tool has shown a success of 100 % on the broken set and 19.5 % on the failed ones.

Thesis (M.S.)--Brigham Young University. Dept. of Computer Science, 2006. / Includes bibliographical references (p. 43-45).