Masaya Oita

Optical implementation of large-scale neural networks using a time-division-multiplexing technique

A new architecture for optical implementation of large-scale neural networks is proposed. This architecture is based on a time-division-multiplexing technique, in which both the neuron state vector and the interconnection matrix are divided in the time domain. Computer simulation and experimental results for associative memories show the effectiveness in implementing large-scale networks.

Optical implementation of an associative neural network model with a stochastic process

An optical associative neural network with a stochastic thresholding procedure has been demonstrated. The use of stochastic processing drastically improved the convergence rate into the correct global minima (recognition rate). The properties of undesirable spurious minima were also investigated. It was found that the spurious minima were represented as the mixed states of the stored vectors. A useful method to estimate the required noise level to vanish the spurious minima is described.

The optical implementation of an intelligent associative memory system

Abstract To simulate brains intelligent associative ability, the architecture of a fully interconnected optoelectronic associative memory system is described. Through a modification of the system cost function, the combination of both the associative ability of neural networks and the logical decision-making of electrical computers is realized. A hybrid-type optical neural network system is implemented to demonstrate the intelligent associative ability. Both computer simulation and experimental results are provided to illustrate the performance of this system.

Character recognition using a dynamic opto-electronic neural network with unipolar binary weights

A novel quantized learning rule with unipolar binary weights which is useful to simplify the artificial neural hardware is reported. An input-dependent thresholding operation is also proposed to remove the unwanted effect due to insufficient contrast ratio of spatial light modulations as a synaptic connection device. The recognition of 26 characters of the alphabet by the single set of an optoelectronic three-layered network was demonstrated experimentally