In particular the critical capacity of the network is increased as well as its capability to store correlated patterns. Chaotic dynamic behaviour(exponentially long transients) of the devices indicates theoverloading of the associative memory. An implementation based on a programmable logic device is here presented. A 16 neurons circuit is implemented whit a XILINK 4020 device. The peculiarity of this solution is the possibility to change parts of the project (weights, transfer function or the whole architecture) with a simple software download of the configuration into the XILINK chip. 1 INTRODUCTION Attractor Neural Networks endowed with local inhibitory feedbacks, have been shown to have interesting computational performances[I].

The field of software simulators for neural networks has been expanding veryrapidly in the last years but their importance is still being underestimated. They must provide increasing levels of assistance forthe design, simulation and analysis of neural networks. With our object-oriented framework (SESAME) we intend to show that very high degrees of transparency, manageability and flexibility forcomplex experiments can be obtained. SESAME's basic design philosophyis inspired by the natural way in which researchers explain their computational models. Experiments are performed with networks of building blocks, which can be extended very easily. Mechanismshave been integrated to facilitate the construction and analysis of very complex architectures.

An analog CMOS VLSI neural processing chip has been designed and fabricated. Thedevice employs "pulse-stream" neural state signalljng, and is capable of computing some 360 million synaptic connections per secood.

IR is typically a sigmoidal function such as (1.2) but other choices than (1.2) are possible and of interest.

The occurence of chaos in recurrent neural networks is supposed to depend on the architecture and on the synaptic coupling strength. It is studied here for a randomly diluted architecture. By normalizing the variance of synaptic weights, we produce a bifurcation parameter, dependent on this variance and on the slope of the transfer function but independent of the connectivity, that allows a sustained activity and the occurence of chaos when reaching a critical value. Even for weak connectivity and small size, we find numerical results in accordance with the theoretical ones previously established for fully connected infinite sized networks. Moreover the route towards chaos is numerically checked to be a quasi-periodic one, whatever the type of the first bifurcation is (Hopf bifurcation, pitchfork or flip).

E (0,00), remains in spite of many real (and 459 460 Finnoff imagined)deficiencies the most widely used network training algorithm, and a vast body of literature documents its general applicability and robustness. In this paper we will draw on the highly developed literature of stochastic approximation theory todemonstrate several asymptotic properties of simple backpropagation.

In visual processing the ability to deal with missing and noisy information iscrucial. Occlusions and unreliable feature detectors often lead to situations where little or no direct information about features is available. Howeverthe available information is usually sufficient to highly constrain the outputs. We discuss Bayesian techniques for extracting class probabilities given partial data. The optimal solution involves integrating overthe missing dimensions weighted by the local probability densities. We show how to obtain closed-form approximations to the Bayesian solution using Gaussian basis function networks.

The action network is embedded in a sensorymotoric systemarchitecture that contains a separate world model. It is continuously fed with short-term predicted spatiotemporal obstacle trajectories, and receives robot state feedback. The action netallows for external switching between alternative planning tasks.It generates goal-directed motor actions - subject to the robot's kinematic and dynamic constraints - such that collisions withmoving obstacles are avoided. Using supervised learning, we distribute examples of the optimal planner mapping over a structure-level adapted parsimonious higher order network. The training database is generated by a Dynamic Programming algorithm. Extensivesimulations reveal, that the local planner mapping is highly nonlinear, but can be effectively and sparsely represented bythe chosen powerful net model. Excellent generalization occurs for unseen obstacle configurations. We also discuss the limitations offeed-forward neurocontrol for growing planning horizons.

Recent research on reinforcement learning has focused on algorithms basedon the principles of Dynamic Programming (DP). One of the most promising areas of application for these algorithms isthe 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 proofsfor 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.

Rep. Germany Abstract Many techniques for model selection in the field of neural networks correspond to well established statistical methods. The method of'stopped training', on the other hand, in which an oversized network is trained until the error on a further validation set of examples deteriorates,then training is stopped, is a true innovation, since model selection doesn't require convergence of the training process. Inthis paper we show that this performance can be significantly enhanced by extending the'nonconvergent model selection method' of stopped training to include dynamic topology modifications (dynamic weight pruning) and modified complexity penalty term methods in which the weighting of the penalty term is adjusted during the training process. 1 INTRODUCTION One of the central topics in the field of neural networks is that of model selection. Both the theoretical and practical side of this have been intensively investigated and a vast array of methods have been suggested to perform this task. A widely used class of techniques starts by choosing an'oversized' network architecture then either removing redundant elements based on some measure of saliency (pruning), adding a further term to the cost function penalizing complexity (penalty terms), and finally, observing the error on a further validation set of examples, then stopping training as soon as this performance begins to deteriorate (stopped training).