The Hopfield Model with Multi-Level Neurons

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 convergence to stable states. The first is a class of "continuous" relations and the second is a class of allowed quantization rules for the neurons. The information capacity for networks from the second class is fOWld to be of order N 3 bits for a network with N neurons. A generalization of the sum of outer products learning rule is developed and investigated as well. © American Institute of Physics 1988