We investigate storage capacity of two types of fully connected layered neural networks with sparse coding when binary patterns are embedded into the networks by a Hebbian learning rule. One of them is a layered network, in which a transfer function of even layers is different from that of odd...

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 investigate the Sherrington–Kirkpatrick (SK) model with spin-S, including S=∞, in a framework of the replica method. We obtain replica symmetric (RS) solutions and one- and two-step replica symmetry breaking (RSB) solutions by using the Parisi scheme, after verifying de Almeida and...

The two-sublattice da Costa–Nobre–Yokoi (CNY) model of spin S⩾1, where spins on each of two sublattices have uniform biquadratic interactions and random exchange interactions only with spins on the other sublattice, is extended to a model on a lattice with three sublattices. We investigate...

We make an estimation of a maximizer of posterior marginals (MPM) as for a multi-valued information symbol by a code-division multiple access (CDMA) demodulator using a multi-valued spreading code sequence within a framework of a Bayesian inference. We calculate an estimation error of the CDMA...

An Ising model with frustration on a three-dimensional lattice is investigated. The system undergoes a phase transition from the paramagnetic to the ferromagnetic state or to a layered antiferromagnetic state. A re-entrant phase transition is observed for the system in some region of the values...

We investigate phase transitions of the XY model on a two-layer triangular lattice when interactions are competing, by using Monte Carlo simulations. For the system with a ferromagnetic interaction on one of two layers and an antiferromagnetic interaction on the other layer, we find two...

We investigate the effect of obstacles on formation of a traffic jam for a traffic flow in a network of city roads. We consider a square lattice of two bonds between two nearest crossings as a network of city roads; we assume that there are three lattice sites in a crossing. We put five...

Occurrence of congestion of packet flow in computer networks is one of the unfavorable problems in packet communication and hence its avoidance should be investigated. We use a neural network model for packet routing control in a computer network proposed in a previous paper by Horiguchi and...