Capacity of Neural Networks where Information is Retrieved from Single Neurons

In this paper we focus on the memory retrieval mechanism in an artificial neural network and suggest an algorithm to increase the memory retrieval rate in the BMatrix neural network. B-matrix is a model of recall by index, where in the activity spreads locally. The B-matrix approach to neural network function accounts for spreading of activity from one region to others based on adjacency of neurons. We propose an algorithm to increase the memory retrieval rate by identifying the inactive nodes in the network and applying Widrow-Hoff learning function to the weighted matrix. We made an attempt to implement the concept of synaptic plasticity in the artificial neural networks to increase the retrieval rate of the network. The change in the state of neurons is also analyzed after the learning algorithm is applied to the network.