Taiwei Lu

Two-dimensional programmable optical neural network.

A 2-D hybrid optical neural network using a high resolution video monitor as a programmable associative memory is proposed. Experiments and computer simulations of the system have been conducted. The high resolution and large dynamic range of the video monitor enable us to implement a hybrid neural network with more neurons and more accurate operation. The system operates in a high speed asynchronous mode due to the parallel feedback loop. The programmability of the system permits the use of orthogonal projection and multilevel recognition algorithms to increase the robustness and storage capacity of the network.

Neural network model using interpattern association

This paper investigates a neural network model-interpattern association (IPA) model-in which the basic logical operations are used to determine the interpattern association (i.e., association between the reference patterns), and simple logical rules are applied to construct tristate interconnections in the network. Computer simulations for the reconstruction of similar English letters embedded in the random noise by the IPA model have shown improved performance compared with the Hopfield model. A 2-D hybrid optical neural network is used to demonstrate the usefulness of the IPA model. Since there are only three gray levels used in the interconnection weight matrix for the IPA model, the dynamic range imposed on a spatial light modulator is rather relaxed, and the interconnections are much simpler than the Hopfield model.

Compact optical neural network using cascaded liquid crystal television.

An optical neural network using two tightly cascaded liquid crystal televisions is presented. This new optical architecture offers compactness in size, ease of alignment, higher light efficiency, better image quality, and low cost. The implementation of the autoassociative and heteroassociative memories is given.

Optical disk based neural network.

Using an optical disk as a large capacity associative memory in an optical neural network is described. The proposed architecture is capable of data processing at high speed.

Optical disk based joint transform correlator

A joint transform correlation system based on optical disks is presented. The operation principle, system considerations, and processing speed are discussed.

Optical parallel logic based on magneto-optic spatial light modulator

Abstract The implementation of sixteen optical parallel boolean logic gates using two magneto-optic spatial light modulators are described. The experimental results are also presented.

Digital optical architectures for multiple matrix multiplication

Abstract Two digital optical architectures utilizing a binary number encoding technique for multiple matrix multiplication are presented. An inner-product method with grating masks is used in one of the architectures, so that multiple matrix multiplication can be performed in parallel. The second architecture, a mixture of systolic array and the inner-product processing method are used. These two architectures can offer high accuracy with moderate speed processing capability.

Redundant-interconnection interpattern-association neural network

We have shown that introducing interconnection redundancy can make a neural network more robust. We describe performances under noisy input and partial input that show that the optimum-redundant interconnection improves both the noise tolerance and the pattern discriminability. Simulated and experimental demonstrations are also provided.

Optical Implementation Of Programmable Neural Networks

A 2-D hybrid optical neural network using a high resolution video monitor as a programmable associative memory is proposed. Experiments and computer simulations of the system have been conducted. The superior resolution and the number of gray levels of the video monitor lead to the implementation of a larger number of neurons and a larger dynamic range. The system operates in a high speed asynchronous mode due to the parallel feedback loop. The programmability of the system permits the use of the Orthogonal Projection(OP) and the Multilevel Recognition (MR) algorithms to increase the error correction ability of the network. Using current integrated optics and electronic technology this optical neural system attains high learning and operational speed.

Adaptive optical system for neural computing

The authors deal with an adaptive optical neural network using Kohonens self-organizing feature map algorithm for unsupervised learning. It is shown that the optical neural network is capable of performing both unsupervised learning and pattern recognition operations simultaneously, by setting matching scores in the learning algorithm. By using a slower learning rate, the construction of the memory matrix becomes topologically more organized. By introducing forbidden regions in the memory space, the neural network would be able to learn new patterns without erasing the old ones. Test results provided show the success of the technique.<<ETX>>