The asymmetric Hopfield model for associative memory
Jinwen Ma · 2005
The theoretical research on associative memory of the asymmetric Hopfield model is presented. The perceptron learning scheme is proposed to store the sample vectors (patterns) in the neural network. For this generalized Hopfield model of n neurons, an upper and a lower bounds for asymptotic memory capacity are obtained respectively to be 2n and (n-1).