An incremental, higher-order, non-recurrent network combines two properties found to be useful for learning sequential tasks: higherorder connectionsand incremental introduction of new units. The network adds higher orders when needed by adding new units that dynamically modify connection weights. Since the new units modify theweights at the next time-step with information from the previous step, temporal tasks can be learned without the use of feedback, thereby greatly simplifying training. Furthermore, a theoretically unlimitednumber of units can be added to reach into the arbitrarily distant past.

We have trained networks of E - II units with short-range connections tosimulate simple cellular automata that exhibit complex or chaotic behaviour. Three levels of learning are possible (in decreasing orderof difficulty): learning the underlying automaton rule, learning asymptotic dynamical behaviour, and learning to extrapolate thetraining history. The levels of learning achieved with and without weight sharing for different automata provide new insight into their dynamics.

Neural network models have been criticized for their inability to make use of compositional representations. In this paper, we describe a series of psychological phenomena that demonstrate the role of structured representations in cognition. These findings suggest that people compare relational representations via a process of structural alignment. This process will have to be captured by any model of cognition, symbolic or subsymbolic.

We present a methodological framework enabling a detailed description ofthe performance of Hopfield-like attractor neural networks (ANN) in the first two iterations. Using the Bayesian approach, wefind that performance is improved when a history-based term is included in the neuron's dynamics. A further enhancement of the network's performance is achieved by judiciously choosing the censored neurons (those which become active in a given iteration) onthe basis of the magnitude of their post-synaptic potentials. Thecontribution of biologically plausible, censored, historydependent dynamicsis especially marked in conditions of low firing activity and sparse connectivity, two important characteristics of the mammalian cortex. In such networks, the performance attained ishigher than the performance of two'independent' iterations, whichrepresents an upper bound on the performance of history-independent networks.

We use statistical mechanics to study generalization in large committee machines.For an architecture with nonoverlapping receptive fields a replica calculation yields the generalization error in the limit of a large number of hidden units.

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 how to set tasks to their submanagersin which high level managers learn how to satisfy them. Sub-managerswho, in turn, learn understand their managers' commands. Theyneed not initially 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 than standard, flat, Q-Iearninglevels, it explores more efficiently and builds a more comprehensive map. 1 INTRODUCTION Straightforward reinforcement learning has been quite successful at some relatively thecomplex tasks like playing backgammon (Tesauro, 1992).

We compare activation functions in terms of the approximation power of their feedforward nets. We consider the case of analog as well as boolean input. 1 Introduction

The overall goal is to reduce spacecraft weight.

The formation of propagating spiral waves is studied in a randomly connected neural network composed of integrate-and-fire neurons with recovery period and excitatory connections using computer simulations. Network activity is initiated by periodic stimulation at a single point. The results suggest that spiral waves can arise in such a network via a sub-critical Hopf bifurcation. 1 Introduction

The algorithm presented performs gradient descent on the weight space of an Artificial Neural Network (ANN), using a finite difference to approximate the gradient The method is novel in that it achieves a computational complexitysimilar to that of Node Perturbation, O(N3), but does not require access to the activity of hidden or internal neurons. This is possible due to a stochastic relation between perturbations at the weights and the neurons of an ANN. The algorithm is also similar to Weight Perturbation in that it is optimal in terms of hardware requirements whenused for the training ofVLSI implementations of ANN's.