A statistical theory for overtraining is proposed. The analysis treats realizable stochastic neural networks, trained with Kullback Leibler loss in the asymptotic case. It is shown that the asymptotic gain in the generalization error is small if we perform early stopping, evenif we have access to the optimal stopping time. Considering cross-validation stopping we answer the question: In what ratio the examples should be divided into training and testing sets in order toobtain the optimum performance. In the non-asymptotic region cross-validated early stopping always decreases the generalization error.Our large scale simulations done on a CM5 are in nice agreement with our analytical findings.

We report on the development of the modular neural system "SEE EAGLE" for the visual guidance of robot pick-and-place actions. Several neural networks are integrated to a single system that visually recognizeshuman hand pointing gestures from stereo pairs of color video images. The output of the hand recognition stage is processed by a set of color-sensitive neural networks to determine the cartesian location of the target object that is referenced by the pointing gesture. Finally, this information is used to guide a robot to grab the target object and put it at another location that can be specified by a second pointing gesture. The accuracy of the current systemallows to identify the location of the referenced target object to an accuracy of 1 cm in a workspace area of 50x50 cm.

On large problems, reinforcement learning systems must use parameterized functionapproximators such as neural networks in order to generalize between similar situations and actions. In these cases there are no strong theoretical results on the accuracy of convergence, and computational resultshave been mixed. In particular, Boyan and Moore reported at last year's meeting a series of negative results in attempting to apply dynamic programming together with function approximation to simple control problems with continuous state spaces. In this paper, we present positive results for all the control tasks they attempted, and for one that is significantly larger. The most important differences are that we used sparse-coarse-coded function approximators (CMACs) whereas they used mostly global function approximators, and that we learned online whereas they learned offline. Boyan and Moore and others have suggested that the problems they encountered could be solved by using actual outcomes ("rollouts"), as in classical Monte Carlo methods, and as in the TD().) algorithm when).

By applying a likelihood splitting criteria to each expert in the HME we "grow" the tree adaptively during training. Secondly,by considering only the most probable path through the tree we may "prune" branches away, either temporarily, or permanently ifthey become redundant. We demonstrate results for the growing and path pruning algorithms which show significant speed ups and more efficient use of parameters over the standard fixed structure in discriminating between two interlocking spirals and classifying 8-bit parity patterns. INTRODUCTION The HME (Jordan & Jacobs 1994) is a tree structured network whose terminal nodes are simple function approximators in the case of regression or classifiers in the case of classification. The outputs of the terminal nodes or experts are recursively combined upwards towards the root node, to form the overall output of the network, by "gates" which are situated at the non-terminal nodes.

Anke Meyer-Base Institute of Technical Informatics Technical University of Darmstadt Darmstadt, Germany 64283 Abstract The dynamics of complex neural networks modelling the selforganization processin cortical maps must include the aspects of long and short-term memory. The behaviour of the network is such characterized by an equation of neural activity as a fast phenomenon andan equation of synaptic modification as a slow part of the neural system. We present a quadratic-type Lyapunov function for the flow of a competitive neural system with fast and slow dynamic variables. We also show the consequences of the stability analysis on the neural net parameters. 1 INTRODUCTION This paper investigates a special class of laterally inhibited neural networks. In particular, we have examined the dynamics of a restricted class of laterally inhibited neural networks from a rigorous analytic standpoint.

We describe the reinforcement learning problem, motivate algorithms whichseek an approximation to the Q function, and present new convergence results for two such algorithms. 1 INTRODUCTION AND BACKGROUND Imagine an agent acting in some environment. At time t, the environment is in some state Xt chosen from a finite set of states. The agent perceives Xt, and is allowed to choose an action at from some finite set of actions. Meanwhile, the agent experiences a real-valued cost Ct, chosen from a distribution which also depends only on Xt and at and which has finite mean and variance. Such an environment is called a Markov decision process, or MDP.

Tel: [ 44] 1223 332815 ajr@eng.cam.ac.uk ABSTRACT We present a Bayesian framework for inferring the parameters of a mixture of experts model based on ensemble learning by variational freeenergy minimisation. The Bayesian approach avoids the over-fitting and noise level underestimation problems of traditional maximum likelihood inference. We demonstrate these methods on artificial problems and sunspot time series prediction. INTRODUCTION The task of estimating the parameters of adaptive models such as artificial neural networks using Maximum Likelihood (ML) is well documented ego Geman, Bienenstock & Doursat (1992). ML estimates typically lead to models with high variance, a process known as "over-fitting".

The supply-chain integrated ordering network (SCION) depot-bookings system automates the planning and scheduling of perishable and nonperishable commodities and the vehicles that carry them into J. Sainsbury depots. This initiative is strategic, enabling the business to make the key move from weekly to daily ordering. The system is mission critical, managing the inward flow of commodities from suppliers into J. Sainsbury's depots. The system leverages AI techniques to provide a business solution that meets challenging functional and performance needs. The SCION depot-bookings system is operational, providing schedules for 22 depots across the United Kingdom.

Reuters is a worldwide company focused on supplying financial and news information to its more than 40,000 subscribers around the world. To enhance the quality and consistency of its customer- support organization, Reuters embarked on a global knowledge development and reuse project. The resulting system is in operational use in North America, Europe, and Asia. The system supports 38 Reuter products worldwide. This article presents a case study of Reuter experience in putting a global knowledge organization in place, building knowledge bases at multiple distributed sites, deploying these knowledge bases in multiple sites around the world, and maintaining and enhancing knowledge bases within a global organizational framework. This project is the first to address issues in multicountry knowledge development and maintenance and multicountry knowledge deployment. These issues are critical for global companies to understand, address, and resolve to effectively gain the benefits of global knowledge systems.

Topics An all-star panel assembled to pose life, and a wealth of other topics were of the technical papers spanned a "Challenge Problems for Artificial Intelligence."