We propose two kinds of architectures for implementing large-scale opto-electronic neural networks. These architectures are based on time- and frequency-division multiplexing (TDM and FDM) techniques, respectively, in which both the neuron state vector and the interconnection matrix are divided in the time- and frequency-domains. The computer simulations, which were carried out for the Hopfield associative memories in the neuron number of 400 and the memory number of 20, have shown their usefulness, providing almost the same recognition rate as the conventional architectures. Using the TDM technique, moreover, we experimentally demonstrated an opto-electronic implementation of the Hopfield associative memory. The experimental results showed that the number of the neurons was effectively increased. We further discuss how to construct the FDM system experimentally.

This paper presents a novel model of optical associative memory using an optoelectronic neurochips, which detects and processes a two-dimensional input image at the same time. The original point of this model is that the optoelectronic neurochips allow direct image processing in terms of parallel input/output interface and parallel neural processing. The operation principle is based on the nonlinear transformation of the input image to the corresponding the point attractor of a fully connected neural network. The learning algorithm is the simulated annealing and the energy of the network state is used as its cost function. The computer simulations show its usefulness and that the maximum number of stored images is 150 in the network with 64 neurons. Moreover, we experimentally demonstrate an optical implementation of the model using the optoelectronic neurochip. The chip consists of two-dimensional array of variable sensitivity photodetectors with 8 16 elements. The experimental results shows that 3 images of size 8 8 were successfully stored in the system. In the case of the input image of size 64 64, the estimated processing speed is 100 times higher than that of the conventional optoelectronic neurochips.