Infants' manipulative exploratory behavior within the environment is a vehicle of cognitive stimulation[McCall 1974]. During this time, infants practice and perfect sensorimotor patterns that become behavioral moduleswhich will be seriated and imbedded in more complex actions. This paper explores the development of such primitive learning systems using an embodied lightweight hand which will be used for a humanoid being developed at the MIT Artificial Intelligence Laboratory[Brooksand Stein 1993]. Primitive grasping procedures are learned from sensory inputs using a connectionist reinforcement algorithm while two submodules preprocess sensory data to recognize the hardness of objects and detect shear using competitive learning and back-propagation algorithm strategies, respectively. This system is not only consistent and quick during theinitial learning stage, but also adaptable to new situations after training is completed.

This paper relates the computational power of Fahlman' s Recurrent Cascade Correlation (RCC) architecture to that of fInite state automata (FSA). While some recurrent networks are FSA equivalent, RCC is not. The paper presents a theoretical analysis of the RCC architecture in the form of a proof describing a large class of FSA which cannot be realized by RCC. 1 INTRODUCTION Recurrent networks can be considered to be defmed by two components: a network architecture, and a learning rule. The former describes how a network with a given set of weights and topology computes its output values, while the latter describes how the weights (and possibly topology) of the network are updated to fIt a specifIc problem. It is possible to evaluate the computational power of a network architecture by analyzing the types of computations a network could perform assuming appropriate connection weights (and topology).

James W. Howse Chaouki T. Abdallah Gregory L. Heileman Department of Electrical and Computer Engineering University of New Mexico Albuquerque, NM 87131 Abstract The process of machine learning can be considered in two stages: model selection and parameter estimation. In this paper a technique is presented for constructing dynamical systems with desired qualitative properties. The approach is based on the fact that an n-dimensional nonlinear dynamical system can be decomposed into one gradient and (n - 1) Hamiltonian systems. Thus,the model selection stage consists of choosing the gradient and Hamiltonian portions appropriately so that a certain behavior is obtainable. To estimate the parameters, a stably convergent learning rule is presented.

Statistically independent features can be extracted by finding a factorial representationof a signal distribution. Principal Component Analysis (PCA) accomplishes this for linear correlated and Gaussian distributedsignals. Independent Component Analysis (ICA), formalized by Comon (1994), extracts features in the case of linear statisticaldependent but not necessarily Gaussian distributed signals. Nonlinear Component Analysis finally should find a factorial representationfor nonlinear statistical dependent distributed signals. This paper proposes for this task a novel feed-forward, information conserving, nonlinear map - the explicit symplectic transformations. It also solves the problem of non-Gaussian output distributions by considering single coordinate higher order statistics. 1 Introduction In previous papers Deco and Brauer (1994) and Parra, Deco, and Miesbach (1995) suggest volume conserving transformations and factorization as the key elements for a nonlinear version of Independent Component Analysis. As a general class of volume conserving transformations Parra et al. (1995) propose the symplectic transformation. It was defined by an implicit nonlinear equation, which leads to a complex relaxation procedure for the function recall. In this paper an explicit form of the symplectic map is proposed, overcoming thus the computational problems.

The Bayesian analysis of neural networks is difficult because a simple priorover weights implies a complex prior distribution over functions. In this paper we investigate the use of Gaussian process priors over functions, which permit the predictive Bayesian analysis forfixed values of hyperparameters to be carried out exactly using matrix operations. Two methods, using optimization and averaging (viaHybrid Monte Carlo) over hyperparameters have been tested on a number of challenging problems and have produced excellent results. 1 INTRODUCTION In the Bayesian approach to neural networks a prior distribution over the weights induces a prior distribution over functions. This prior is combined with a noise model, which specifies the probability of observing the targets t given function values y, to yield a posterior over functions which can then be used for predictions. For neural networks the prior over functions has a complex form which means that implementations must either make approximations (e.g.

In systems that process sensory data there is frequently a model matching stage where class hypotheses are combined to recognize a complex entity. We introduce a new model of parallelism, the Single Function Multiple Data (SFMD) model, appropriate to this stage. SFMD functionality can be added with small hardware expense to certain existing SIMD architectures, and as an incremental addition to the programming model. Adding SFMD to an SIMD machine will not only allow faster model matching, but also increase its flexibility as a general purpose machine and its scope in performing the initial stages of sensory processing. 1 INTRODUCTION In systems that process sensory data there is frequently a post-classification stage where several independent class hypotheses are combined into the recognition of a more complex entity. Examples include matching word models with a string of observation probabilities, and matching visual object models with collections of edges or other features. Current parallel computer architectures for processing sensory data focus on the classification and pre-classification stages (Hammerstrom 1990).This is reasonable, as those stages likely have the largest potential for speedup through parallel execution. Nonetheless, the model-matching stage is also suitable for parallelism, as each model may be matched independently of the others. We introduce a new style of parallelism, Single Function Multiple Data (SFMD), that is suitable for the model-matching stage.

Learning long-term dependencies is not as difficult with NARX recurrent neural networks.

Search for the largest (or the smallest) among a number of input data, Le., the winner-take-all (WTA) action, is an essential part of intelligent data processing such as data retrieval in associative memories [3], vector quantization circuits [4], Kohonen's self-organizing maps [5] etc. In addition to the maximum or minimum search, data sorting also plays an essential role in a number of signal processing such as median filtering in image processing, evolutionary algorithms in optimizing problems [6] and so forth.

However, ANNs are usually costly to train, preventing one from trying many different representations. In this paper, we address this problem by introducing and evaluating three new measures for quickly estimating ANN input representation quality. Two of these, called [DBleaves and Min (leaves), consistently outperform Rendell and Ragavan's (1993) blurring measure in accurately ranking different input representations for ANN learning on three difficult, real-world datasets.

Department of Electrical and Computer Engineering University of Queensland St. Lucia Qld 4072 Australia Abstract We define a Gamma multi-layer perceptron (MLP) as an MLP with the usual synaptic weights replaced by gamma filters (as proposed byde Vries and Principe (de Vries and Principe, 1992)) and associated gain terms throughout all layers. We derive gradient descent update equations and apply the model to the recognition of speech phonemes. We find that both the inclusion of gamma filters in all layers, and the inclusion of synaptic gains, improves the performance of the Gamma MLP. We compare the Gamma MLP with TDNN, Back-Tsoi FIR MLP, and Back-Tsoi I1R MLP architectures, and a local approximation scheme. We find that the Gamma MLP results in an substantial reduction in error rates. 1 INTRODUCTION 1.1 THE GAMMA FILTER Infinite Impulse Response (I1R) filters have a significant advantage over Finite Impulse Response(FIR) filters in signal processing: the length of the impulse response is uncoupled from the number of filter parameters.