We propose a model for a system with middle temporal neurons and medial superior temporal (MST) neurons by using a three-layered autoencoder. Noise effect is taken into account by using the framework of statistical physics. We define a cost function of the autoencoder, from which a learning rule...

We investigate storage capacity of a fully connected layered neural network with Q(⩾2)-states clock neurons, including Q=∞ (corresponding to oscillatory neurons) and with intra-layer connections, where random Q-values patterns are embedded into the network by the Hebbian learning rule. We...

We propose a neural network model of working memory with one-compartmental neurons and investigate its dynamical properties. We assume that the model consists of excitatory neurons and inhibitory neurons; all the neurons are connected to each other. The excitatory neurons are distinguished as...

We investigate a packet flow problem in a computer network within a framework of statistical physics. We propose a model for packet routing control by putting a neural network at each node. The energy function for the whole system is defined in order to express competition among queue length,...