Reinforcement Learning by Policy Search

One objective of artificial intelligence is to model the behavior of an intelligent agent interacting with its environment. The environment's transformations can be modeled as a Markov chain, whose state is partially observable to the agent and affected by its actions; such processes are known as partially observable Markov decision processes (POMDPs). While the environment's dynamics are assumed to obey certain rules, the agent does not know them and must learn. In this dissertation we focus on the agent's adaptation as captured by the reinforcement learning framework. This means learning a policy---a mapping of observations into actions---based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. The set of policies is constrained by the architecture of the agent's controller. POMDPs require a controller to have a memory. We investigate controllers with memory, including controllers with external memory, finite state controllers and distributed controllers for multi-agent systems. For these various controllers we work out the details of the algorithms which learn by ascending the gradient of expected cumulative reinforcement. Building on statistical learning theory and experiment design theory, a policy evaluation algorithm is developed for the case of experience re-use. We address the question of sufficient experience for uniform convergence of policy evaluation and obtain sample complexity bounds for various estimators. Finally, we demonstrate the performance of the proposed algorithms on several domains, the most complex of which is simulated adaptive packet routing in a telecommunication network.

A Note on the Generalization Performance of Kernel Classifiers with Margin

We present distribution independent bounds on the generalization misclassification performance of a family of kernel classifiers with margin. Support Vector Machine classifiers (SVM) stem out of this class of machines. The bounds are derived through computations of the $V_gamma$ dimension of a family of loss functions where the SVM one belongs to. Bounds that use functions of margin distributions (i.e. functions of the slack variables of SVM) are derived.

Learning-Based Approach to Real Time Tracking and Analysis of Faces

This paper describes a trainable system capable of tracking faces and facialsfeatures like eyes and nostrils and estimating basic mouth features such as sdegrees of openness and smile in real time. In developing this system, we have addressed the twin issues of image representation and algorithms for learning. We have used the invariance properties of image representations based on Haar wavelets to robustly capture various facial features. Similarly, unlike previous approaches this system is entirely trained using examples and does not rely on a priori (hand-crafted) models of facial features based on optical flow or facial musculature. The system works in several stages that begin with face detection, followed by localization of facial features and estimation of mouth parameters. Each of these stages is formulated as a problem in supervised learning from examples. We apply the new and robust technique of support vector machines (SVM) for classification in the stage of skin segmentation, face detection and eye detection. Estimation of mouth parameters is modeled as a regression from a sparse subset of coefficients (basis functions) of an overcomplete dictionary of Haar wavelets.

Probabilistic Independence Networks for Hidden Markov Probability Models

Graphical techniques for modeling the dependencies of randomvariables have been explored in a variety of different areas includingstatistics, statistical physics, artificial intelligence, speech recognition, image processing, and genetics.Formalisms for manipulating these models have been developedrelatively independently in these research communities. In this paper weexplore hidden Markov models (HMMs) and related structures within the general framework of probabilistic independencenetworks (PINs). The paper contains a self-contained review of the basic principles of PINs.It is shown that the well-known forward-backward (F-B) and Viterbialgorithms for HMMs are special cases of more general inference algorithms forarbitrary PINs. Furthermore, the existence of inference and estimationalgorithms for more general graphical models provides a set of analysistools for HMM practitioners who wish to explore a richer class of HMMstructures.Examples of relatively complex models to handle sensorfusion and coarticulationin speech recognitionare introduced and treated within the graphical model framework toillustrate the advantages of the general approach.

Neural Networks

We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view learning algorithms as methods for finding parameter values that look probable in the light of the data. We discuss basic issues in representation and learning, and treat some of the practical issues that arise in fitting networks to data. We also discuss links between neural networks and the general formalism of graphical models.

The Unsupervised Acquisition of a Lexicon from Continuous Speech

We present an unsupervised learning algorithm that acquires a natural-language lexicon from raw speech. The algorithm is based on the optimal encoding of symbol sequences in an MDL framework, and uses a hierarchical representation of language that overcomes many of the problems that have stymied previous grammar-induction procedures. The forward mapping from symbol sequences to the speech stream is modeled using features based on articulatory gestures. We present results on the acquisition of lexicons and language models from raw speech, text, and phonetic transcripts, and demonstrate that our algorithm compares very favorably to other reported results with respect to segmentation performance and statistical efficiency.

Learning from Incomplete Data

Real-world learning tasks often involve high-dimensional data sets with complex patterns of missing features. In this paper we review the problem of learning from incomplete data from two statistical perspectives---the likelihood-based and the Bayesian. The goal is two-fold: to place current neural network approaches to missing data within a statistical framework, and to describe a set of algorithms, derived from the likelihood-based framework, that handle clustering, classification, and function approximation from incomplete data in a principled and efficient manner. These algorithms are based on mixture modeling and make two distinct appeals to the Expectation-Maximization (EM) principle (Dempster, Laird, and Rubin 1977)---both for the estimation of mixture components and for coping with the missing data.

Inteligencia artificial para la detección y el diagnóstico de fallos

L' ús de tècniques de la intel·ligència artificial per a la detecció, la diagnòsi i control d' errors

¿Pueden pensar las máquinas? Una evaluación del problema de la inteligencia artificial mediante el equilibrio refractivo

Revisión del problema de la filosofía de la Inteligencia Artificial a la vista del Equilibrio refractivo. La revisión del problema se lleva a cabo para mostrar como "¿pueden pensar las máquinas?" sólo se ha evaluado en los terminos humanos. El equilibrio refractivo se plantea como una herramienta para definir conceptos de tal modo que la experiencia y los preceptos se encuentren en equilibrio, para con él construir una definición de pensar que no esté limitada exclusivamente a "pensar tal y como lo hacen los humanos".

An artificial economy based on reinforcement learning and agent based modeling

In this paper, we employ techniques from artificial intelligence such as reinforcement learning and agent based modeling as building blocks of a computational model for an economy based on conventions. First we model the interaction among firms in the private sector. These firms behave in an information environment based on conventions, meaning that a firm is likely to behave as its neighbors if it observes that their actions lead to a good pay off. On the other hand, we propose the use of reinforcement learning as a computational model for the role of the government in the economy, as the agent that determines the fiscal policy, and whose objective is to maximize the growth of the economy. We present the implementation of a simulator of the proposed model based on SWARM, that employs the SARSA(λ) algorithm combined with a multilayer perceptron as the function approximation for the action value function.

Ergonomía. Fundamentos para el desarrollo de soluciones ergonómicas

En este texto se presentan algunos conceptos y marcos teóricos útiles para el análisis del trabajo en ergonomía. El objetivo es mostrar los conceptos de base para el estudio del trabajo en la tradición de la ergonomía de la actividad, y analizar de manera general algunos de los modelos empleados para el análisis de una actividad de trabajo. Inicialmente se abordan los principios teóricos de la ergonomía y los principios que provienen de la fisiología, la biomecánica, la psicología y la sociología; también se presentan los acercamientos metodológicos empleados en esta misma perspectiva para el análisis de actividades de trabajo. Se parte del principio de que un estudio ergonómico del trabajo se puede llevar a cabo desde una doble perspectiva: la perspectiva analítica y la perspectiva comprensiva.

Automatic mass segmentation in mammographic images

Aquesta tesi està emmarcada dins la detecció precoç de masses, un dels símptomes més clars del càncer de mama, en imatges mamogràfiques. Primerament, s'ha fet un anàlisi extensiu dels diferents mètodes de la literatura, concloent que aquests mètodes són dependents de diferent paràmetres: el tamany i la forma de la massa i la densitat de la mama. Així, l'objectiu de la tesi és analitzar, dissenyar i implementar un mètode de detecció robust i independent d'aquests tres paràmetres. Per a tal fi, s'ha construït un patró deformable de la massa a partir de l'anàlisi de masses reals i, a continuació, aquest model és buscat en les imatges seguint un esquema probabilístic, obtenint una sèrie de regions sospitoses. Fent servir l'anàlisi 2DPCA, s'ha construït un algorisme capaç de discernir aquestes regions són realment una massa o no. La densitat de la mama és un paràmetre que s'introdueix de forma natural dins l'algorisme.

KAIFIA: Knowledge assisted intelligent framework for information access

Accessing information, which is spread across multiple sources, in a structured and connected way, is a general problem for enterprises. A unified structure for knowledge representation is urgently needed to enable integration of heterogeneous information resources. Topic Maps seem to be a solution for this problem. The Topic Map technology enables connecting information, through concepts and relationships, and their occurrences across multiple systems. In this paper, we address this problem by describing a framework built on topic maps, to support the current need of knowledge management. New approaches for information integration, intelligent search and topic map exploration are introduced within this framework.

Knowledge-elicitation and data-mining: fusing human and industrial plant information

Knowledge-elicitation is a common technique used to produce rules about the operation of a plant from the knowledge that is available from human expertise. Similarly, data-mining is becoming a popular technique to extract rules from the data available from the operation of a plant. In the work reported here knowledge was required to enable the supervisory control of an aluminium hot strip mill by the determination of mill set-points. A method was developed to fuse knowledge-elicitation and data-mining to incorporate the best aspects of each technique, whilst avoiding known problems. Utilisation of the knowledge was through an expert system, which determined schedules of set-points and provided information to human operators. The results show that the method proposed in this paper was effective in producing rules for the on-line control of a complex industrial process. (C) 2005 Elsevier Ltd. All rights reserved.

Fusing data-mining and knowledge elicitation for the supervisory control of an aluminium plate mill

Knowledge-elicitation is a common technique used to produce rules about the operation of a plant from the knowledge that is available from human expertise. Similarly, data-mining is becoming a popular technique to extract rules from the data available from the operation of a plant. In the work reported here knowledge was required to enable the supervisory control of an aluminium hot strip mill by the determination of mill set-points. A method was developed to fuse knowledge-elicitation and data-mining to incorporate the best aspects of each technique, whilst avoiding known problems. Utilisation of the knowledge was through an expert system, which determined schedules of set-points and provided information to human operators. The results show that the method proposed in this paper was effective in producing rules for the on-line control of a complex industrial process.