Abstract
We investigate the system error tolerance of optical connectionist architectures, which utilize liquid crystal spatial light modulators to represent neurons and weights in a neural network configuration. Experimental and computer simulation results show training on one layer networks compensates for errors in the optical and electronic hardware. The mathematical description of the least mean square algorithm used to train these networks shows that this is to be expected. This tolerance, however, is not shown in multiple layer networks implemented with similar architectures. To overcome problems associated with linear dependence between training patterns and maintain the error tolerance of the one layer machines (without going to multiple layer networks), an architecture with higher level interconnections is proposed. This fully interconnected second order architecture requires only a single optical pass before updating the weights. It also uses a very similar training algorithm to that of the single layer network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D.Psaltis and R.A.Athale, “High accuracy computation with linear analog optical systems: a critical study”, Appl. Opt. 25 p. 3071 (1986).
M.Kranzdorf, K.M.Johnson, B.J.Bigner & L.Zhang, “An Optical Connectionist Machine with Polarization-Based Bipolar Weights”, Opt. Eng. 28 p. 844 (1989).
M.G.Robinson, K.M.Johnson, L.Zhang & B.J.Bigner, “Optical neural networks using smectic liquid crystals”, OE LASE meeting in Los Angeles, 14–19 Jan. 1990. SPIE Proc. 1215.
A.P.Ittycheriah, J.F.Walkup, T.F.Krile & S.L.Lee, “Outer product processor using polarization encoding”, Appl. Opt. 29 p. 275 (1990)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Robinson, M.G., Johnson, K.M., Zhang, L. (1990). Network Analysis of an Optically Implemented Connectionist Architecture. In: International Neural Network Conference. Springer, Dordrecht. https://doi.org/10.1007/978-94-009-0643-3_20
Download citation
DOI: https://doi.org/10.1007/978-94-009-0643-3_20
Publisher Name: Springer, Dordrecht
Print ISBN: 978-0-7923-0831-7
Online ISBN: 978-94-009-0643-3
eBook Packages: Springer Book Archive