We analyse the effects of analog noise on the synaptic arithmetic during MultiLayer Perceptron training, by expanding the cost function to include noise-mediated penalty terms. Predictions are made in the light of these calculations which suggest that fault tolerance, generalisation ability and learning trajectory should be improved by such noise-injection. Extensive simulation experiments on two distinct classification problems substantiate the claims. The results appear to be perfectly general for all training schemes where weights are adjusted incrementally, and have wide-ranging implications for all applications, particularly those involving "inaccurate" analog neural VLSI.

Recently, both connectionist and symbolic methods have been developed for biasing learning with prior knowledge lFu, 1989; Towell et a/., 1990; Ourston and Mooney, 1990]. Most ofthese methods revise an imperfect knowledge base (usually obtained from a domain expert) to fit a set of empirical data. Some of these methods have been successfully applied to real-world tasks, such as recognizing promoter sequences in DNA [Towell et ai., 1990; Ourston and Mooney, 1990]. The results demonstrate that revising an expert-given knowledge base produces more accurate results than learning from training data alone.

Given a set oft raining examples, determining the appropriate number of free parameters is a challenging problem. Constructive learning algorithms attempt to solve this problem automatically by adding hidden units, and therefore free parameters, during learning. We explore an alternative class of algorithms-called metamorphosis algorithms-in which the number of units is fixed, but the number of free parameters gradually increases during learning. The architecture we investigate is composed of RBF units on a lattice, which imposes flexible constraints on the parameters of the network. Virtues of this approach include variable subset selection, robust parameter selection, multiresolution processing, and interpolation of sparse training data.

This is motivated by experimental evidence that these phenomena may be subserved by the same mechanisms. An important aspect of this model is that ocular dominance segregation can occur when input activity is both distributed, and positively correlated between the eyes. This allows investigation of the dependence of the pattern of ocular dominance stripes on the degree of correlation between the eyes: it is found that increasing correlation leads to narrower stripes. Experiments are suggested to test whether such behaviour occurs in the natural system.

We demonstrate the use of a digital signal processing board to construct hybrid networks consisting of computer model neurons connected to a biological neural network. This system operates in real time.

Mechanisms of gastric rhythm generation in the isolated stomatogastric ganglion of spiny lobsters: Bursting pacemaker potentials, synaptic interactions and muscarinic modulation.

Several researchers have implemented comput.at.ional models of biological audit.ory

Within a simple test-bed, application of feed-forward neurocontrol for short-term planning of robot trajectories in a dynamic environment is studied. The action network is embedded in a sensorymotoric system architecture that contains a separate world model. It is continuously fed with short-term predicted spatiotemporal obstacle trajectories, and receives robot state feedback. The action net allows 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 with moving obstacles are avoided.

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).

Some improved generalization properties are demonstrat.ed