1 March 1997 Design of fiber optic adaline neural networks
Author Affiliations +
Based on possible optoelectronic realization of adaptive filters and equalizers using fiber optic tapped delay lines and spatial light modulators we describe the design of a single-layer fiber optic Adaline neural network that can be used as a bit pattern classifier. In our design, we employ as few electronic devices as possible and use optical computation to utilize the advantages of optics in processing speed, parallelism, and interconnection. The described new optical neural network design is for optical processing of guided light wave signals, not electronic signals. We analyze the convergence or learning characteristics of the optoelectronic Adaline in the presence of errors in the hardware. We show that with such an optoelectronic Adaline it is possible to detect a desired code word/token/header with good accuracy.
Anjan K. Ghosh, Anjan K. Ghosh, Jim Trepka, Jim Trepka, } "Design of fiber optic adaline neural networks," Optical Engineering 36(3), (1 March 1997). https://doi.org/10.1117/1.601138 . Submission:


Optoelectronic Gabor detector for transient signals
Proceedings of SPIE (July 31 1991)
Fiber optic Adaline neural networks
Proceedings of SPIE (February 01 1993)
Optoelectronic neuron implementation
Proceedings of SPIE (February 22 2005)

Back to Top