A CCD-based processor that we call the NNC2 is presented. The NNC2 implements a fully connected 192-input, 32-output two-layer network and can be cascaded to form multilayer networks or used in parallel for additional inputor output nodes. The device computes 1.92 x 10

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.

This paper applies the theory of Probably Approximately Correct (PAC) learning to multiple output feedforward threshold networks in which the weights conform to certain equivalences. It is shown that the sample size for reliable learning can be bounded above by a formula similar to that required for single output networks with no equivalences. The best previously obtainedbounds are improved for all cases.

Biological retinas extract spatial and temporal features in an attempt to reduce the complexity of performing visual tasks. We have built and tested a silicon retina which encodes several useful temporal features found in vertebrate retinas.The cells in our silicon retina are selective to direction, highly sensitive to positive contrast changes around an ambient light level, and tuned to a particular velocity. Inhibitory connections in the null direction performthe direction selectivity we desire. This silicon retina is on a 4.6 x 6.8mm die and consists of a 47 x 41 array of photoreceptors.

Networks for reconstructing a sparse or noisy function often use an edge field to segment the function into homogeneous regions, This approach assumes that these regions do not overlap or have disjoint parts, which is often false. For example, images which contain regions split by an occluding objectcan't be properly reconstructed using this type of network. We have developed a network that overcomes these limitations, using support maps to represent the segmentation of a signal. In our approach, the support ofeach region in the signal is explicitly represented. Results from an initial implementation demonstrate that this method can reconstruct images and motion sequences which contain complicated occlusion.

In this work, the problem of establishing routes through random MINs (RMINs) in a shared-memory, distributed computing system is addressed.

This paper considers the problem of expressing predicate calculus in connectionist networksthat are based on energy minimization. Given a firstorder-logic knowledgebase and a bound k, a symmetric network is constructed (like a Boltzman machine or a Hopfield network) that searches for a proof for a given query. If a resolution-based proof of length no longer than k exists, then the global minima of the energy function that is associated with the network represent such proofs. The network that is generated is of size cubic in the bound k and linear in the knowledge size. There are no restrictions on the type of logic formulas that can be represented.

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.

Feedforward networks composed of units which compute a sigmoidal function ofa weighted sum of their inputs have been much investigated. We tested the approximation and estimation capabilities of networks using functions more complex than sigmoids. Three classes of functions were tested: polynomials, rational functions, and flexible Fourier series. Unlike sigmoids,these classes can fit nonmonotonic functions. They were compared on three problems: prediction of Boston housing prices, the sunspot count, and robot arm inverse dynamics. The complex units attained clearlysuperior performance on the robot arm problem, which is a highly nonmonotonic, pure approximation problem. On the noisy and only mildly nonlinear Boston housing and sunspot problems, differences among the complex units were revealed; polynomials did poorly, whereas rationals and flexible Fourier series were comparable to sigmoids. 1 Introduction

This is an extension of previous work on recognizing isolated digits.