We present a Parallel Distributed Semantic (PDS) Network architecture that addresses the problems of sequencing and ambiguity resolution in natural language understanding. A PDS Network stores phrases and their meanings using multiple PDP networks, structured in the form of a semantic net. A mechanism called Propagation Filters is employed: (1) to control communication between networks, (2) to properly sequence the components of a phrase, and (3) to resolve ambiguities. Simulation results indicate that PDS Networks and Propagation Filters can successfully represent high-level knowledge, can be trained relatively quickly, and provide for parallel inferencing at the knowledge level. 1 INTRODUCTION Backpropagation has shown considerable potential for addressing problems in natural language processing (NLP). However, the traditional PDP [Rumelhart and McClelland, 1986] approach of using one (or a small number) of backprop networks for NLP has been plagued by a number of problems: (1) it has been largely unsuccessful at representing high-level knowledge, (2) the networks are slow to train, and (3) they are sequential at the knowledge level.

We present the "Multi-State Time Delay Neural Network" (MS-TDNN) as an extension of the TDNN to robust word recognition.

Self-organizing feature maps like the Kohonen map (Kohonen, 1989, Ritter et al., 1990) not only provide a plausible explanation for the formation of maps in brains, e.g. in the visual system (Obermayer et al., 1990), but have also been applied to problems like vector quantization, or robot arm control (Martinetz et al., 1990). The underlying organizing principle is the preservation of neighborhood relations. For this principle to lead to a most useful map, the topological structure of the output space must roughly fit the structure of the input data. However, in technical 1141 1142 Bauer, Pawelzik, and Geisel applications this structure is often not a priory known. For this reason several attempts have been made to modify the Kohonen-algorithm such, that not only the weights, but also the output space topology itself is adapted during learning (Kangas et al., 1990, Martinetz et al., 1991). Our contribution is also concerned with optimal output space topologies, but we follow a different approach, which avoids a possibly complicated structure of the output space. First we describe a quantitative measure for the preservation of neighborhood relations in maps, the topographic product P. The topographic product had been invented under the name of" wavering product" in nonlinear dynamics in order to optimize the embeddings of chaotic attractors (Liebert et al., 1991).

Ion channels are the dynamical systems of the nervous system. Their distribution within the membrane governs not only communication of information between neurons, but also how that information is integrated within the cell. Here, an argument is presented for an'anti-Hebbian' rule for changing the distribution of voltage-dependent ion channels in order to flatten voltage curvatures in dendrites. Simulations show that this rule can account for the self-organisation of dynamical receptive field properties such as resonance and direction selectivity. It also creates the conditions for the faithful conduction within the cell of signals to which the cell has been exposed. Various possible cellular implementations of such a learning rule are proposed, including activity-dependent migration of channel proteins in the plane of the membrane.

Three methods for improving the performance of (gaussian) radial basis function (RBF) networks were tested on the NETtaik task. In RBF, a new example is classified by computing its Euclidean distance to a set of centers chosen by unsupervised methods. The application of supervised learning to learn a non-Euclidean distance metric was found to reduce the error rate of RBF networks, while supervised learning of each center's variance resulted in inferior performance. The best improvement in accuracy was achieved by networks called generalized radial basis function (GRBF) networks. In GRBF, the center locations are determined by supervised learning. After training on 1000 words, RBF classifies 56.5% of letters correct, while GRBF scores 73.4% letters correct (on a separate test set). From these and other experiments, we conclude that supervised learning of center locations can be very important for radial basis function learning.

Several parallel analogue algorithms, based upon mean field theory (MFT) approximations to an underlying statistical mechanics formulation, and requiring an externally prescribed annealing schedule, now exist for finding approximate solutions to difficult combinatorial optimisation problems. They have been applied to the Travelling Salesman Problem (TSP), as well as to various issues in computational vision and cluster analysis. I show here that any given MFT algorithm can be combined in a natural way with notions from the areas of constrained optimisation and adaptive simulated annealing to yield a single homogenous and efficient parallel relaxation technique, for which an externally prescribed annealing schedule is no longer required. The results of numerical simulations on 50-city and 100-city TSP problems are presented, which show that the ensuing algorithms are typically an order of magnitude faster than the MFT algorithms alone, and which also show, on occasion, superior solutions as well. 1 INTRODUCTION Several promising parallel analogue algorithms, which can be loosely described by the term "deterministic annealing", or "mean field theory (MFT) annealing", have *also at Theoretical Division and Center for Nonlinear Studies, MSB213, Los Alamos National Laboratory, Los Alamos, NM 87545.

Unfortunately, convergence of normal WT A networks is extremely sensitive to the magnitudes of their weights, which must be hand-tuned and which generally only provide the right amount of inhibition across a relatively small range of initial conditions. This paper presents Dynamjcally Adaptive Winner-Telke-All (DA WTA) netw rls, which use a regulatory unit to provide the competitive inhibition to the units in the network. The DA WT A regulatory unit dynamically adjusts its level of activation during competition to provide the right amount of inhibition to differentiate between competitors and drive a single winner. This dynamic adaptation allows DA WT A networks to perform the winner-lake-all function for nearly any network size or initial condition.

I present a modular network architecture and a learning algorithm based on incremental dynamic programming that allows a single learning agent to learn to solve multiple Markovian decision tasks (MDTs) with significant transfer of learning across the tasks. I consider a class of MDTs, called composite tasks, formed by temporally concatenating a number of simpler, elemental MDTs. The architecture is trained on a set of composite and elemental MDTs. The temporal structure of a composite task is assumed to be unknown and the architecture learns to produce a temporal decomposition. It is shown that under certain conditions the solution of a composite MDT can be constructed by computationally inexpensive modifications of the solutions of its constituent elemental MDTs. 1 INTRODUCTION Most applications of domain independent learning algorithms have focussed on learning single tasks. Building more sophisticated learning agents that operate in complex environments will require handling multiple tasks/goals (Singh, 1992). Research effort on the scaling problem has concentrated on discovering faster learning algorithms, and while that will certainly help, techniques that allow transfer of learning across tasks will be indispensable for building autonomous learning agents that have to learn to solve multiple tasks. In this paper I consider a learning agent that interacts with an external, finite-state, discrete-time, stochastic dynamical environment and faces multiple sequences of Markovian decision tasks (MDTs).

A routing scheme that uses a neural network has been developed that can aid in establishing point-to-point communication routes through multistage interconnection networks (MINs). The neural network is a network of the type that was examined by Hopfield (Hopfield, 1984 and 1985). In this work, the problem of establishing routes through random MINs (RMINs) in a shared-memory, distributed computing system is addressed. The performance of the neural network routing scheme is compared to two more traditional approaches - exhaustive search routing and greedy routing. The results suggest that a neural network router may be competitive for certain RMIN s. 1 INTRODUCTION A neural network has been developed that can aid in establishing point-topoint communication routes through multistage interconnection networks (MINs) (Goudreau and Giles, 1991).

Intrator (1990) proposed a feature extraction method that is related to recent statistical theory (Huber, 1985; Friedman, 1987), and is based on a biologically motivated model of neuronal plasticity (Bienenstock et al., 1982). This method has been recently applied to feature extraction in the context of recognizing 3D objects from single 2D views (Intrator and Gold, 1991). Here we describe experiments designed to analyze the nature of the extracted features, and their relevance to the theory and psychophysics of object recognition. 1 Introduction Results of recent computational studies of visual recognition (e.g., Poggio and Edelman, 1990) indicate that the problem of recognition of 3D objects can be effectively reformulated in terms of standard pattern classification theory. According to this approach, an object is represented by a few of its 2D views, encoded as clusters in multidimentional space. Recognition of a novel view is then carried out by interpo-460 3D Object Recognition Using Unsupervised Feature Extraction 461 lating among the stored views in the representation space.