This paper examines whether temporal difference methods for training connectionist networks, such as Suttons's TO('\) algorithm, can be successfully appliedto complex real-world problems. A number of important practical issues are identified and discussed from a general theoretical perspective. Thesepractical issues are then examined in the context of a case study in which TO('\) is applied to learning the game of backgammon from the outcome of self-play. This is apparently the first application of this algorithm to a complex nontrivial task. It is found that, with zero knowledge built in, the network is able to learn from scratch to play the entire game at a fairly strong intermediate level of performance, which is clearly better than conventional commercial programs, and which in fact surpasses comparable networks trained on a massive human expert data set. The hidden units in these network have apparently discovered useful features, a longstanding goal of computer games research.

Animal locomotion patterns are controlled by recurrent neural networks called central pattern generators (CPGs). Although a CPG can oscillate autonomously, its rhythm and phase must be well coordinated with the state of the physical system using sensory inputs. In this paper we propose a learning algorithm for synchronizing neural and physical oscillators with specific phase relationships. Sensory input connections are modified by the and input signals. Simulations showcorrelation between cellular activities that the learning rule can be used for setting sensory feedback connections to a CPG as well as coupling connections between CPGs. 1 CENTRAL AND SENSORY MECHANISMS IN LOCOMOTION CONTROL Patterns of animal locomotion, such as walking, swimming, and fiying, are generated by recurrent neural networks that are located in segmental ganglia of invertebrates and spinal cords of vertebrates (Barnes and Gladden, 1985).

Because of the complexity of the application and the large amount of data, the problem cannot be solved by using a single method. The solution we propose is to build multimodules NNarchitectures where several NN cooperate together. Such system suffer from generic problem for whom we propose solutions. They allow to reach accurate performances for multi-valued function approximations and probability estimations. The results are compared with six other methods which have been used for this problem. We show that the methodology we have developed is general and can be used for a large variety of applications.

After being trained on some dozen Bach chorales using error backpropagation, the system is capable of producing four-part chorales in the style of J .s.Bach, given a one-part melody. Our system solves a musical real-world problem on a performance level appropriate for musical practice. HARMONET's power is based on (a) a new coding scheme capturing musically relevant information and (b) the integration of backpropagation and symbolic algorithms in a hierarchical system, combining theadvantages of both. 1 INTRODUCTION Neural approaches to music processing have been previously proposed (Lischka, 1989) and implemented (Mozer, 1991)(Todd, 1989). The promise neural networks offer is that they may shed some light on an aspect of human creativity that doesn't seem to be describable in terms of symbols and rules. Ultimately what music is (or isn't) lies in the eye (or ear) of the beholder.

Marques Pereira Dipartimento di Informatica Universita di Trento Via Inama 7, Trento, TN 38100 ITALY Abstract Learning a map from an input set to an output set is similar to the problem ofreconstructing hypersurfaces from sparse data (Poggio and Girosi, 1990). In this framework, we discuss the problem of automatically selecting "minimal"surface data. The objective is to be able to approximately reconstruct the surface from the selected sparse data. We show that this problem is equivalent to the one of compressing information by data removal andthe one oflearning how to teach. Our key step is to introduce a process that statistically selects the data according to the model. During the process of data selection (learning how to teach) our system (teacher) is capable of predicting the new surface, the approximated one provided by the selected data.

Neurons encoding simple visual features in area VI such as orientation, direction of motion and color are organized in retinotopic maps. However, recentphysiological experiments have shown that the responses of many neurons in VI and other cortical areas are modulated by the direction ofgaze. We have developed a neural network model of the visual cortex to explore the hypothesis that visual features are encoded in headcentered coordinatesat early stages of visual processing. New experiments are suggested for testing this hypothesis using electrical stimulations and psychophysical observations.

Using the double-step target displacement paradigm the mechanisms underlying armtrajectory modification were investigated. Using short (10-110 msec) inter-stimulus intervals the resulting hand motions were initially directed in between the first and second target locations. The kinematic features of the modified motions were accounted for by the superposition scheme, which involves the vectorial addition of two independent point-topoint motionunits: one for moving the hand toward an internally specified location and a second one for moving between that location and the final target location. The similarity between the inferred internally specified locations andpreviously reported measured endpoints of the first saccades in double-step eye-movement studies may suggest similarities between perceived targetlocations in eye and hand motor control.

We develop a model-independent method for characterizing the reliability of neural responses to brief stimuli. This approach allows us to measure the discriminability of similar stimuli, based on the real-time response of a single neuron. Neurophysiological data were obtained from a movementsensitive neuron(HI) in the visual system of the blowfly Calliphom erythrocephala. Furthermore,recordings were made from blowfly photoreceptor cells to quantify the signal to noise ratios in the peripheral visual system. As photoreceptors form the input to the visual system, the reliability oftheir signals ultimately determines the reliability of any visual discrimination task. For the case of movement detection, this limit can be computed, and compared to the HI neuron's reliability. Under favorable conditions,the performance of the HI neuron closely approaches the theoretical limit, which means that under these conditions the nervous system adds little noise in the process of computing movement from the correlations of signals in the photoreceptor array.

Visual attention is the ability to dynamically restrict processing to a subset of the visual field. Researchers have long argued that such a mechanism is necessary to efficiently perform many intermediate level visual tasks. This paper describes VISIT, a novel neural network model of visual attention.

Two projection based feedforward network learning methods for modelfree regressionproblems are studied and compared in this paper: one is the popular back-propagation learning (BPL); the other is the projection pursuit learning (PPL).