A generic model of oscillating cortex, which assumes "minimal" coupling justified by known anatomy, is shown to function as an associative memory, using previously developed theory. The network has explicit excitatory neurons with local inhibitory interneuron feedback that forms a set of nonlinear oscillators coupled only by long range excitatofy connections. Using a local Hebb-like learning ru...

We apply evolutionary algorithms to Hop eld model of associative memory. Previously we reported that a genetic algorithm using ternary chromosomes evolves the Hebb-rule associative memory to enhance its storage capacity by pruning some connections. This paper describes a genetic algorithm using real-encoded chromosomes which successfully evolves over-loaded Hebbian synaptic weights to function ...

Two existing high capacity training rules for the standard Hopfield architecture associative memory are examined. Both rules, based on the perceptron learning rule produce asymmetric weight matrices, for which the simple dynamics (only point attractors) of a symmetric network can no longer be guaranteed. This paper examines the consequences of imposing a symmetry constraint in learning. The mea...

Imagination is considered an important component of the creative process, and many psychologists agree that imagination is based on our perceptions, experiences, and conceptual knowledge, recombining them into novel ideas and impressions never before experienced. As an attempt to model this account of imagination, we introduce the Associative Conceptual Imagination (ACI) framework that uses ass...

We present an exact equilibrium analysis of a class of associative memory models with spatial structure in the form of combined shortand long-range synapses. We solve the models for sequential and parallel dynamics by use of random-field techniques and we find that competing interactions induce continuous and discontinuous bifurcations of the overlap order parameter as well as coexistence of di...

We propose a pattern recognition system based on an architecture close to the one found in human visual cortex which is called Hypercolumns. We use this discrete parametric representation in connection with a sparsley coding associative memory. In principle the application of such a representation appears to be very well suited for data reduction and pattern recognition processes and is part of...

A novel single-chip shared buffer ATM switch architecture is presented, in which a Content Addressable Memory (CAM) is used to control access to the shared buffer RAM, in place of a linked list mechanism. Switch operation is explained in detail, and performance is compared to that of a Linked List switch. Memory capacity requirements are decreased, and cell storage and retrieval is simplified. ...

We investigate how geometric properties translate into functional properties in sparse networks of computing elements. Specifically, we determine how the eigenvalues of the interconnection graph (which in turn reflect connectivity properties) relate to the quantities, number of items stored, amount of error-correction, radius of attraction, and rate of convergence, in an associative memory mode...

An extension to Hopfield’s model of associative memory is studied in the present work. In particular, this paper is focused in giving solutions to the two main problems present in the model: the apparition of spurious patterns in the learning phase (implying the well-known and undesirable effect of storing the opposite pattern) and the problem of its reduced capacity (the probability of error i...

The consequences of imposing a sign constraint on the standard Hopfield architecture associative memory model, trained using perceptron like learning rules, is examined. Such learning rules have been shown to have capacity of at most half of their unconstrained versions. This paper reports experimental investigations into the consequences of constraining the sign of the network weights in terms...