Thispaper presents a neural-net solution to a resource allocation problem that arises in providing local access to the backbone of a wide-area communication network.The problem is described in terms of an energy function that can be mapped onto an analog computational network. Simulation results characterizing the performance of the neural computation are also presented. INTRODUCTION This paper presents a neural-network solution to a resource allocation problem that arises in providing access to the backbone of a communication network. 1 Inthe field of operations research, this problem was first known as the warehouse location problem and heuristics for finding feasible, suboptimal solutions have been developed previously.2.

A"'ir Dembo Information Systems Laboratory, Stanford University Stanford, CA 94305 Ofer Zeitouni Laboratory for Information and Decision Systems MIT, Cambridge, MA 02139 ABSTRACT A class of high dens ity assoc iat ive memories is constructed, starting from a description of desired properties those should exhib it. These propert ies include high capac ity, controllable bas ins of attraction and fast speed of convergence. Fortunately enough, the resulting memory is implementable by an artificial Neural Net. I NfRODUCTION Most of the work on assoc iat ive memories has been structure oriented, i.e.. given a Neural architecture, efforts were directed towards the analysis of the resulting network. Issues like capacity, basins of attractions, etc. were the main objects to be analyzed cf., e.g.

Synthetic neural nets[1,2] represent an active and growing research field. Fundamental issues, as well as practical implementations with electronic and optical devices are being studied. In addition, several learning algorithms have been studied, for example stochastically adaptivesystems[3] based on many-body physics optimization concepts[4,5]. Signal processing in the optical domain has also been an active field of research. A wide variety of nonlinear all-optical devices are being studied, directed towards applications bothin optical computating and in optical switching.

It can be shown that a straightforward generalization of the tropism phenomenon allows the efficient implementation of effective algorithms which appear to respond "intelligently" to changing environmental conditions. Examples of the utilization of tropistic processing techniques will be presented in this paper in applications entailing simulated behavior synthesis, path-planning, pattern analysis (clustering), and engineering design optimization. INTRODUCTION The goal of this paper is to present an intuitive overview of a general unsupervised procedure for addressing a variety of system control and cost minimization problems. This procedure is hased on the idea of utilizing "stimuli" produced by the environment in which the systems are designed to operate as basis for dynamically providing the necessary system parameter updates. This is by no means a new idea: countless examples of this approach abound in nature, where innate reactions to specific stimuli ("tropisms" or "taxis" --not to be confused with "instincts") provide organisms with built-in first-order control laws for triggering varied responses [8].

Oregon Graduate Center, Beaverton, OR 97006 ABSTRACT The efficient realization, using current silicon technology, of Very Large Connection Networks (VLCN) with more than a billion connections requires that these networks exhibit a high degree of communication locality. Real neural networks exhibit significant locality, yet most connectionist/neural network models have little. In this paper, the connectivity requirements of a simple associative network are analyzed using communication theory. Several techniques based on communication theory are presented that improve the robustness ofthe network in the face of sparse, local interconnect structures. Also discussed are some potential problems when information is distributed too widely. INTRODUCTION Connectionist/neural network researchers are learning to program networks that exhibit a broad range of cognitive behavior.

Lyle J. Borg-Graham Harvard-MIT Division of Health Sciences and Technology and Center for Biological Information Processing, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139 ABSTRACT A computer model of the hippocampal pyramidal cell (HPC) is described which integrates data from a variety of sources in order to develop a consistent descriptionfor this cell type. The model presently includes descriptions of eleven nonlinear somatic currents of the HPC, and the electrotonic structure of the neuron is modelled with a soma/short-cable approximation. Model simulations qualitatively or quantitatively reproduce a wide range of somatic electrical behavior i HPCs, and demonstrate possible roles for the various currents in information processing. There are several substrates for neuronal computation, including connectivity, synapses,morphometries of dendritic trees, linear parameters of cell membrane, as well as nonlinear, time-varying membrane conductances, also referred to as currents or channels. In the classical description of neuronal function, the contribution of membrane channels is constrained to that of generating the action potential, setting firing threshold, and establishing the relationship between (steady-state) stimulus intensity and firing frequency.

The McCulloch/Pitts model discussed in [1] was one of the earliest neural network models to be analyzed. Some computational properties of what we call a Hopfield Associative Memory Network (HAMN):similar to the McCulloch/Pitts model was discussed by Hopfield in [2]. The HAMN can be measured quantitatively by defining and evaluating the information capacity as [2-6] have shown, but this network fails to exhibit more complex computational capabilities that neural network have due to its simplified structure. The HAMN belongs to a class of networks which we call static. In static networks the learning and recall procedures areseparate.

QUALITATIVERESULTS Analysis of the weights produced by training a network is an exceedingly difficult problem, which we have only been able to approach qualitatively. In Figure 1 we present a diagram showing the connection strengths in a network with 651 input units and no hidden units.

Learning algorithms for the neural network which search for the "most probable" member of P can then be designed. Statistical tests which decide if the "true" or environmental probability distribution is in P can also be developed. Example applications of the theory to the highly nonlinear back-propagation learning algorithm, and the networks of Hopfield and Anderson are discussed. INTRODUCTION A connectionist system is a network of simple neuron-like computing elements which can store and retrieve information, and most importantly make generalizations. Using terminology suggested by Rumelhart & McClelland 1, the computing elements of a connectionist system are called units, and each unit is associated with a real number indicating its activity level. The activity level of a given unit in the system can also influence the activity level of another unit. The degree of influence between two such units is often characterized by a parameter of the system known as a connection strength. During the information retrievalprocess some subset of the units in the system are activated, and these units in turn activate neighboring units via the inter-unit connection strengths.

Instead, a signal space approach is used to gain new insights via ease of analysis and geometrical interpretation.