In this paper we re-investigate windowing for rule learning algorithms. We show that, contrary to previous results for decision tree learning, windowing can in fact achieve significant run-time gains in noise-free domains and explain the different behavior of rule learning algorithms by the fact that they learn each rule independently. The main contribution of this paper is integrative windowing, a new type of algorithm that further exploits this property by integrating good rules into the final theory right after they have been discovered. Thus it avoids re-learning these rules in subsequent iterations of the windowing process. Experimental evidence in a variety of noise-free domains shows that integrative windowing can in fact achieve substantial run-time gains. Furthermore, we discuss the problem of noise in windowing and present an algorithm that is able to achieve run-time gains in a set of experiments in a simple domain with artificial noise.

In this paper we re-investigate windowing for rule learning algorithms. We show that, contrary to previous results for decision tree learning, windowing can in fact achieve significant run-time gains in noise-free domains and explain the different behavior of rule learning algorithms by the fact that they learn each rule independently. The main contribution of this paper is integrative windowing, a new type of algorithm that further exploits this property by integrating good rules into the final theory right after they have been discovered. Thus it avoids re-learning these rules in subsequent iterations of the windowing process. Experimental evidence in a variety of noise-free domains shows that integrative windowing can in fact achieve substantial run-time gains. Furthermore, we discuss the problem of noise in windowing and present an algorithm that is able to achieve run-time gains in a set of experiments in a simple domain with artificial noise.

The format of the conference will include paper presentations, invited speakers, panel discussions, workshops, and planning and scheduling competitions.

We present a system, CREWS_NS, that is used in the long-term scheduling of drivers and guards for the Dutch Railways. CREWS_NS schedules the work of about 5000 people. CREWS_NS is built on top of CREWS, a scheduling tool for speeding the development of scheduling applications. CREWS heavily relies on the use of AI techniques and has been built as a white-box system, in the sense that the planner can perceive what is going on, can interact with the system by proposing alternatives or querying decisions, and can adapt the behavior of the system to changing circumstances. Scheduling can be done in automatic, semiautomatic, or manual mode. CREWS has mechanisms for dealing with the constant changes that occur in input data, can identify the consequences of the change, and guides the planner in accommodating the changes in the already built schedules (rescheduling).

Understanding the mind is one of the great "holy grails" of twentieth-century research. Regardless of training, most people who come in contact with the field of AI are at least partially motivated by the glimmer of hope that they will get a better understanding of the mind. This quest, of course, is a rich and complex one. It is easy to get mired in minutiae along the way, be they the optimization of an algorithm, the details of a mental model, or the intricacies of a logical argument. Thagard's book attempts to call us back to the larger picture and to draw in new devotees -- and, in general, he succeeds.

An important characteristic of many logics for Artificial Intelligence is their nonmonotonicity. This means that adding a formula to the premises can invalidate some of the consequences. There may, however, exist formulae that can always be safely added to the premises without destroying any of the consequences: we say they respect monotonicity. Also, there may be formulae that, when they are a consequence, can not be invalidated when adding any formula to the premises: we call them conservative. We study these two classes of formulae for preferential logics, and show that they are closely linked to the formulae whose truth-value is preserved along the (preferential) ordering. We will consider some preferential logics for illustration, and prove syntactic characterization results for them. The results in this paper may improve the efficiency of theorem provers for preferential logics.

Neural one-unit learning rules for the problem of Independent Component Analysis (ICA) and blind source separation are introduced. In these new algorithms, every ICA neuron develops into a separator that finds one of the independent components. The learning rules use very simple constrained Hebbianjanti-Hebbian learning in which decorrelating feedback may be added. To speed up the convergence of these stochastic gradient descent rules, a novel computationally efficient fixed-point algorithm is introduced. 1 Introduction Independent Component Analysis (ICA) (Comon, 1994; Jutten and Herault, 1991) is a signal processing technique whose goal is to express a set of random variables as linear combinations of statistically independent component variables. The main applications of ICA are in blind source separation, feature extraction, and blind deconvolution.

We have calculated analytical expressions for how the bias and variance of the estimators provided by various temporal difference value estimation algorithms change with offline updates over trials in absorbing Markov chains using lookup table representations. We illustrate classes of learning curve behavior in various chains, and show the manner in which TD is sensitive to the choice of its stepsize and eligibility trace parameters. 1 INTRODUCTION A reassuring theory of asymptotic convergence is available for many reinforcement learning (RL) algorithms. What is not available, however, is a theory that explains the finite-term learning curve behavior of RL algorithms, e.g., what are the different kinds of learning curves, what are their key determinants, and how do different problem parameters effect rate of convergence. Answering these questions is crucial not only for making useful comparisons between algorithms, but also for developing hybrid and new RL methods. In this paper we provide preliminary answers to some of the above questions for the case of absorbing Markov chains, where mean square error between the estimated and true predictions is used as the quantity of interest in learning curves.

We compare different methods to combine predictions from neural networks trained on different bootstrap samples of a regression problem. One of these methods, introduced in [6] and which we here call balancing, is based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. We show how to estimate these individual errors from the residuals on validation patterns. Weighting factors for the different networks follow from a quadratic programming problem. On a real-world problem concerning the prediction of sales figures and on the well-known Boston housing data set, balancing clearly outperforms other recently proposed alternatives as bagging [1] and bumping [8]. 1 EARLY STOPPING AND BOOTSTRAPPING Stopped training is a popular strategy to prevent overfitting in neural networks.

By now it is widely accepted that learning a task from scratch, i.e., without any prior knowledge, is a daunting undertaking. Humans, however, rarely attempt to learn from scratch. They extract initial biases as well as strategies how to approach a learning problem from instructions and/or demonstrations of other humans. For learning control, this paper investigates how learning from demonstration can be applied in the context of reinforcement learning. We consider priming the Q-function, the value function, the policy, and the model of the task dynamics as possible areas where demonstrations can speed up learning. In general nonlinear learning problems, only model-based reinforcement learning shows significant speedup after a demonstration, while in the special case of linear quadratic regulator (LQR) problems, all methods profit from the demonstration. In an implementation of pole balancing on a complex anthropomorphic robot arm, we demonstrate that, when facing the complexities of real signal processing, model-based reinforcement learning offers the most robustness for LQR problems. Using the suggested methods, the robot learns pole balancing in just a single trial after a 30 second long demonstration of the human instructor.