%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 12:57:23 PM @TECHREPORT{Moerland-97.2, author = {Moerland, Perry and Fiesler, Emile and Saxena, Indu}, projects = {Idiap}, title = {Discrete All-Positive Multilayer Perceptrons for Optical Implementation}, type = {Idiap-RR}, number = {Idiap-RR-02-1997}, year = {1997}, institution = {IDIAP}, note = {Accepted for publication in {\em Optical Engineering}}, abstract = {All-optical multilayer perceptrons differ in various ways from the ideal neural network model. Examples are the use of non-ideal activation functions which are truncated, asymmetric, and have a non-standard gain, restriction of the network parameters to non-negative values, and the limited accuracy of the weights. In this paper, a backpropagation-based learning rule is presented that compensates for these non-idealities and enables the implementation of all-optical multilayer perceptrons where learning occurs under control of a computer. The good performance of this learning rule, even when using a small number of weight levels, is illustrated by a series of experiments including the non-idealities.}, pdf = {https://publications.idiap.ch/attachments/reports/1997/rr97-02.pdf}, postscript = {ftp://ftp.idiap.ch/pub/reports/1997/rr97-02.ps.gz}, ipdmembership={learning}, }