THE HOPFIELD MODEL WITH MUL TI-LEVEL NEURONS Michael Fleisher Department of Electrical Engineering Technion Israel Institute of Technology Haifa 32000, Israel The Hopfield neural network. model for associative memory is generalized. The generalization replaces two state neurons by neurons taking a richer set of values. Two classes of neuron input output relations are developed guaranteeing conv...

In this paper two different approaches to solve Sudoku puzzles with neural networks are presented. The first approach is proposed by J.J. Hopfield. He tries to solve the Sudoku puzzle with help of a Hopfield network and treated the problem as an integer optimization problem that is also used for the solution of the well known Traveling Salesmen Problem (TSP). Second solution uses the Hopfield n...

In this paper, we propose a continuous hysteresis neurons Hopfield neural network architecture for efficiently solving crossbar switch problems. A Hopfield neural network architecture with continuous hysteresis and its collective computational properties are studied. It is proved theoretically and confirmed by simulating the randomly generated Hopfield neural network with continuous hysteresis ...

Understanding the memory capacity of neural networks remains a challenging problem in implementing artificial intelligence systems. In this paper, we address the notion of capacity with respect to Hopfield networks and propose a dynamic approach to monitoring a network’s capacity. We define our understanding of capacity as the maximum number of stored patterns which can be retrieved when probed...

The brain can reproduce memories from partial data; this ability is critical for memory recall. The process of memory recall has been studied using autoassociative networks such as the Hopfield model. This kind of model reliably converges to stored patterns that contain the memory. However, it is unclear how the behavior is controlled by the brain so that after convergence to one configuration,...

The brain can reproduce memories from partial data; this ability is critical for memory recall. The process of memory recall has been studied using auto-associative networks such as the Hopfield model. This kind of model reliably converges to stored patterns which contain the memory. However, it is unclear how the behavior is controlled by the brain so that after convergence to one configuratio...

Identifying corresponding features in an image sequence is an important issue in motion analysis. We present a solution based on the assumption of smooth motion using point features. Local constraints are used to make the method robust against occlusion and imperfect feature extraction. A global cost function is defined which is minimised by a mapping of feature points onto a 2-D Hopfield neura...

A new technique is used to reduce the classic Hodgkin-Huxley model to a two-dimensional neuronal model which retains the essential features of the full description. The resulting equations are similar in spirit to those of the FitzHugh-Nagumo model, but they exhibit some essential diierences which provide a more accurate representation of the full dynamics. By further simplifying the two-dimens...