Abstract
The use of a multilayer neural network is indicated in those cases of pattern classification where the input has a relatively low spatial complexity, eg 16 x 16 pixels. Such an input size arises in the post-segmentation stage of handwritten character recognition, or more generally after a pre-processing stage on more complex input scenes. Since the pre-processing is likely to be optical, eg Fourier or wavelet transform, it is of interest to consider the construction of an optical neural network where the training might be slow, due to the speed of the interface of the programmable weight matrices, but the classification stage would proceed at rates superior to electronics. This involves the use of stand-alone analog optical device for the intermediate layer of neural thresholding elements (hidden layer) in between the two layers of interconnects. The critical aspects of such an approach are the engineering of the programmable interconnect, the characteristics of the hidden layer optical device, the question of optical subtraction, and the use of discretization techniques to avoid the deleterious consequences of analog noise. The first aspect will be discussed in this summary and the other aspects will be more fully reported at the conference. The optical design of the system was presented previously [1], and this report will concentrate on the practical results.
© 1995 Optical Society of America
PDF ArticleMore Like This
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
Lin Zhang and Kristina M. Johnson
MT3 OSA Annual Meeting (FIO) 1992
Christoph Berger, Neil Collings, and Timothée Jost
OTuE.5 Optics in Computing (IP) 1997