Electrophysiological studies (Cynader and Berman 1972, Robinson 1972) showed that the intermediate layer of SC is topographically organized into a motor map. The location of active neurons in this area was found to be related to the oculomotor error (Le.

We propose a very simple, and well principled way of computing the optimal step size in gradient descent algorithms. The online version is very efficient computationally, and is applicable to large backpropagation networks trained on large data sets. The main ingredient is a technique for estimating the principal eigenvalue(s) and eigenvector(s) of the objective function's second derivative matrix (Hessian), which does not require to even calculate the Hessian. Several other applications of this technique are proposed for speeding up learning, or for eliminating useless parameters. 1 INTRODUCTION Choosing the appropriate learning rate, or step size, in a gradient descent procedure such as backpropagation, is simultaneously one of the most crucial and expertintensive part of neural-network learning. We propose a method for computing the best step size which is both well-principled, simple, very cheap computationally, and, most of all, applicable to online training with large networks and data sets.

The planar thallium-201 myocardial perfusion scintigram is a widely used diagnostic technique for detecting and estimating the risk of coronary artery disease. Neural networks learned to interpret 100 thallium scintigrams as determined by individual expert ratings. Standard error backpropagation was compared to standard LMS, and LMS combined with one layer of RBF units. Using the "leave-one-out" method, generalization was tested on all 100 cases. Training time was determined automatically from cross-validation perfonnance. Best perfonnance was attained by the RBF/LMS network with three hidden units per view and compares favorably with human experts.

One way to speed up reinforcement learning is to enable learning to happen simultaneously at multiple resolutions in space and time. This paper shows how to create a Q-Iearning managerial hierarchy in which high level managers learn how to set tasks to their submanagers who, in turn, learn how to satisfy them. Sub-managers need not initially understand their managers' commands. They simply learn to maximise their reinforcement in the context of the current command. We illustrate the system using a simple maze task.. As the system learns how to get around, satisfying commands at the multiple levels, it explores more efficiently than standard, flat, Q-Iearning and builds a more comprehensive map. 1 INTRODUCTION Straightforward reinforcement learning has been quite successful at some relatively complex tasks like playing backgammon (Tesauro, 1992).

In [5], a new incremental cascade network architecture has been presented. This paper discusses the properties of such cascade networks and investigates their generalization abilities under the particular constraint of small data sets. The evaluation is done for cascade networks consisting of local linear maps using the Mackey Glass time series prediction task as a benchmark. Our results indicate that to bring the potential of large networks to bear on the problem of ning extracting information from small data sets without run the risk of overjitting, deeply cascaded network architectures are more favorable than shallow broad architectures that contain the same number of nodes. 1 Introduction For many real-world applications, a major constraint for the successful learning from examples is the limited number of examples available. Thus, methods are required, that can learn from small data sets. This constraint makes the problem of generalization particularly hard.

Matched filtering has been one of the most powerful techniques employed for transient detection. Here we will show that a dynamic neural network outperforms the conventional approach. When the artificial neural network (ANN) is trained with supervised learning schemes there is a need to supply the desired signal for all time, although we are only interested in detecting the transient. In this paper we also show the effects on the detection agreement of different strategies to construct the desired signal. The extension of the Bayes decision rule (011 desired signal), optimal in static classification, performs worse than desired signals constructed by random noise or prediction during the background.

The relationships between learning, development and evolution in Nature is taken seriously, to suggest a model of the developmental process whereby the genotypes manipulated by the Genetic Algorithm (GA) might be expressed to form phenotypic neural networks (NNet) that then go on to learn. ONTOL is a grammar for generating polynomial NN ets for time-series prediction. Genomes correspond to an ordered sequence of ONTOL productions and define a grammar that is expressed to generate a NNet. The NNet's weights are then modified by learning, and the individual's prediction error is used to determine GA fitness. A new gene doubling operator appears critical to the formation of new genetic alternatives in the preliminary but encouraging results presented.

Recent research on reinforcement learning has focused on algorithms based on the principles of Dynamic Programming (DP). One of the most promising areas of application for these algorithms is the control of dynamical systems, and some impressive results have been achieved. However, there are significant gaps between practice and theory. In particular, there are no con vergence proofs for problems with continuous state and action spaces, or for systems involving nonlinear function approximators (such as multilayer perceptrons). This paper presents research applying DPbased reinforcement learning theory to Linear Quadratic Regulation (LQR), an important class of control problems involving continuous state and action spaces and requiring a simple type of nonlinear function approximator. We describe an algorithm based on Q-Iearning that is proven to converge to the optimal controller for a large class of LQR problems. We also describe a slightly different algorithm that is only locally convergent to the optimal Q-function, demonstrating one of the possible pitfalls of using a nonlinear function approximator with DPbased learning.

We are interested in the use of analog neural networks for recognizing visual objects. Objects are described by the set of parts they are composed of and their structural relationship. Structural models are stored in a database and the recognition problem reduces to matching data to models in a structurally consistent way. The object recognition problem is in general very difficult in that it involves coupled problems of grouping, segmentation and matching. We limit the problem here to the simultaneous labelling of the parts of a single object and the determination of analog parameters. This coupled problem reduces to a weighted match problem in which an optimizing neural network must minimize E(M, p) LO'i MO'i WO'i(p), where the {MO'd are binary match variables for data parts i to model parts a and {Wai(P)} are weights dependent on parameters p.

A parallel stochastic algorithm is investigated for error-descent learning and optimization in deterministic networks of arbitrary topology. No explicit information about internal network structure is needed. The method is based on the model-free distributed learning mechanism of Dembo and Kailath. A modified parameter update rule is proposed by which each individual parameter vector perturbation contributes a decrease in error. A substantially faster learning speed is hence allowed. Furthermore, the modified algorithm supports learning time-varying features in dynamical networks. We analyze the convergence and scaling properties of the algorithm, and present simulation results for dynamic trajectory learning in recurrent networks.