Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Photonic components for neural net implementations using incoherent-coherent holographic interconnections

Not Accessible

Your library or personal account may give you access

Abstract

A novel photonic architecture for neuralnetwork implementation was recently proposed,1 which incorporates a hybrid incoherent/coherent recording and readout scheme for the formation and utilization of highly multiplexed volume holograms. In this paper we discuss three of the essential optoelectronic components integrated within this architecture: volume holographic interconnections, multifunction spatial light modulators (SLM's), and two-dimensional incoherent/coherent source arrays.2 The volume holographic interconnections use a novel double angularly multiplexed incoherent/coherent recording and reconstruction technique that minimizes both the recording-induced and readout-induced crosstalk inherent in conventional fan-out/fan-in interconnections, permits incoherent summation of interconnection-weighted inputs, and optimizes overall interconnection throughput efficiency. Multifunction optoelectronic SLM's are used to implement dualchannel two dimensional neuron unit arrays and thus incorporate the detection, amplification, functional implementation (e.g., sigmoidal response), and optical modulation required in the neuron unit planes.

© 1990 Optical Society of America

PDF Article
More Like This
Photonic neural-network architecture based on incoherent-coherent holographic interconnections

B. K. Jenkins, A. R. Tanguay, S. Piazzolla, G. C. Petrisor, and P. Asthana
MVV2 OSA Annual Meeting (FIO) 1990

Photonic neural networks based on incoherent/coherent double angular multiplexing

B. Keith Jenkins, Armand R. Tanguay, Anupam Madhukar, and Christoph von der Malsburg
MBB1 OSA Annual Meeting (FIO) 1992

Photonic Implementations of Neural Networks

C. Kyriakakis, Z. Karim, A. R. Tanguay, R. F. Cartland, A. Madhukar, S. Piazzolla, B. K. Jenkins, C. B. Kuznia, A. A. Sawchuk, and C. von der Malsburg
OTuB1 Optical Computing (IP) 1995

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.