Associative memory and amount of mutual information in a chaotic neural network introducing function typed synaptic weights

So far, in associative memory search problems chaotic neural networks have constant synaptic weights to store patterns. In this paper, we propose a chaotic neural network (CNN) which has function typed synaptic weights to store patterns in order to make a better performance of the retrieval of the stored patterns. In stored patterns retrieval simulation, it is clarified that our proposed method is superior to the conventional CNN, that is, which has constant synaptic weights. We also propose a simple calculation algorithm of amount of mutual information for a chaotic neural network and shows that the edge of chaos on the CNN is much relation to amount of mutual information.