In supervised learning, learning from queries rather than from random examples can improve generalization performance significantly. Westudy the performance of query learning for problems where the student cannot learn the teacher perfectly, which occur frequently in practice. As a prototypical scenario of this kind, we consider a linear perceptron student learning a binary perceptron teacher. Two kinds of queries for maximum information gain, i.e., minimum entropy, are investigated: Minimum student space entropy (MSSE)queries, which are appropriate if the teacher space is unknown, and minimum teacher space entropy (MTSE) queries, which can be used if the teacher space is assumed to be known, but a student of a simpler form has deliberately been chosen. We find that for MSSE queries, the structure of the student space determines theefficacy of query learning, whereas MTSE queries lead to a higher generalization error than random examples, due to a lack of feedback about the progress of the student in the way queries are selected.

Statistical models of discrete time series have a wide range of applications, most notably to problems in speech recognition (Juang & Rabiner, 1991) and molecular biology (Baldi, Chauvin, Hunkapiller, & McClure, 1992). A common problem in these fields is to find a probabilistic model, and a set of model parameters, that 436 LawrenceK. Saul, Michael I. Jordan account for sequences of observed data. Hidden Markov models (HMMs) have been particularly successful at modeling discrete time series. One reason for this is the powerful learning rule (Baum) 1972») a special case of the Expectation-Maximization (EM) procedure for maximum likelihood estimation (Dempster) Laird) & Rubin) 1977).

In young barn owls raised with optical prisms over their eyes, these auditory maps are shifted to stay in register with the visual map, suggesting that the visual input imposes a frame of reference on the auditory maps. However, the optic tectum, the first site of convergence of visual with auditory information, is not the site of plasticity for the shift of the auditory maps; the plasticity occurs instead in the inferior colliculus, which contains an auditory map and projects into the optic tectum. We explored a model of the owl remapping in which a global reinforcement signal whose delivery is controlled by visual foveation. A hebb learning rule gated by reinforcement learnedto appropriately adjust auditory maps. In addition, reinforcement learning preferentially adjusted the weights in the inferior colliculus, as in the owl brain, even though the weights were allowed to change throughout the auditory system. This observation raisesthe possibility that the site of learning does not have to be genetically specified, but could be determined by how the learning procedure interacts with the network architecture.

This paper presents a rigorous characterization of how a general nonlinear learning machine generalizes during the training process when it is trained on a random sample using a gradient descent algorithm based on reduction of training error. It is shown, in particular, that best generalization performance occurs, in general, before the global minimum of the training error is achieved. The different roles played by the complexity of the machine class and the complexity of the specific machine in the class during learning are also precisely demarcated. 1 INTRODUCTION In learning machines such as neural networks, two major factors that affect the'goodness of fit' of the examples are network size (complexity) and training time. These are also the major factors that affect the generalization performance of the network. Many theoretical studies exploring the relation between generalization performance and machine complexity support the parsimony heuristics suggested by Occam's razor, towit that amongst machines with similar training performance one should opt for the machine of least complexity.

Four overlapping patterns (1-4) are presented sequentially.

It is widely accepted that the use of more compact representations than lookup tables is crucial to scaling reinforcement learning (RL) algorithms to real-world problems. Unfortunately almost all of the theory of reinforcement learning assumes lookup table representations. Inthis paper we address the pressing issue of combining function approximation and RL, and present 1) a function approximator basedon a simple extension to state aggregation (a commonly used form of compact representation), namely soft state aggregation, 2) a theory of convergence for RL with arbitrary, but fixed, soft state aggregation, 3) a novel intuitive understanding of the effect of state aggregation on online RL, and 4) a new heuristic adaptive state aggregation algorithm that finds improved compact representations by exploiting the non-discrete nature of soft state aggregation. Preliminary empirical results are also presented.

We develop a principled strategy to sample a function optimally for function approximation tasks within a Bayesian framework. Using ideas from optimal experiment design, we introduce an objective function (incorporating both bias and variance) to measure the degree ofapproximation, and the potential utility of the data points towards optimizing this objective. We show how the general strategy canbe used to derive precise algorithms to select data for two cases: learning unit step functions and polynomial functions. In particular, we investigate whether such active algorithms can learn the target with fewer examples. We obtain theoretical and empirical resultsto suggest that this is the case. 1 INTRODUCTION AND MOTIVATION Learning from examples is a common supervised learning paradigm that hypothesizes atarget concept given a stream of training examples that describes the concept. In function approximation, example-based learning can be formulated as synthesizing anapproximation function for data sampled from an unknown target function (Poggio and Girosi, 1990). Active learning describes a class of example-based learning paradigms that seeks out new training examples from specific regions of the input space, instead of passively accepting examples from some data generating source. By judiciously selecting ex- 594 KahKay Sung, Parlha Niyogi amples instead of allowing for possible random sampling, active learning techniques can conceivably have faster learning rates and better approximation results than passive learning methods. This paper presents a Bayesian formulation for active learning within the function approximation framework.

It is well known that axons are neural processes specialized for transmitting information overrelatively long distances in the nervous system. Impulsive electrical disturbances known as action potentials are normally initiated near the cell body of a neuron when the voltage across the cell membrane crosses a threshold. These pulses are then propagated with a fairly stereotypical shape at a more or less constant velocitydown the length of the axon. Consequently, axons excel at precisely preserving the relative timing of threshold crossing events but do not preserve any of the initial signal shape. Information, then, is presumably encoded in the relative timing of action potentials.

This paper presents NeuroChess, a program which learns to play chess from the final outcome of games. NeuroChess learns chess board evaluation functions, represented by artificial neural networks.

AM techniques were first introduced in soft-competitive learning algorithms[l]. Thistraining procedure was later shown to be closely related to Expectation-Maximization algorithms used by the statistical estimation community[2].