For industrial use, adaptive resonance theory (ART) neural networks have the potential of becoming an important component in a variety of commercial and military systems. Efficient software emulations of these networks are adequate in many of today’s low-end applications such as information retrieval or group technology. But for larger applications, special-purpose hardware is required to achieve the expected performance requirements. Direct electronic implementation of this network model has proven difficult to scale to large-input dimensionality owing to the high degree of interconnectivity between layers. Here, a new hardware implementation design of ART1 is proposed that handles input dimensions of practical size. It efficiently combines the advantages of optical and electronic devices to produce a stand-alone ART1 processor. Parallel computations are relegated to free-space optics, while serial operations are performed in VLSI electronics. One possible physical realization of this architecture is proposed. No hardware has as yet been built.
© 1992 Optical Society of AmericaFull Article | PDF Article
More Like This
Donald C. Wunsch, David J. Morris, Rick L. McGann, and Thomas P. Caudell
Appl. Opt. 32(8) 1399-1407 (1993)
Marta Ruiz-Llata and Horacio Lamela-Rivera
Appl. Opt. 44(12) 2366-2376 (2005)
Appl. Opt. 26(23) 5104-5111 (1987)