%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 12:57:46 PM @INPROCEEDINGS{Moerland-96.3, author = {Moerland, Perry and Fiesler, Emile and Saxena, Indu}, keywords = {activation function, liquid crystal light valve (LCLV), non-negative neural networks, optical multilayer perceptron, weight discretization}, projects = {Idiap}, title = {Overcoming Inaccuracies in Optical Multilayer Perceptrons}, booktitle = {Proceedings of the First International Symposium on Neuro-Fuzzy Systems (AT'96)}, year = {1996}, publisher = {AATI}, location = {Lausanne, Switzerland}, 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 use of limited accuracy for the weights. In this paper an adaptation of the backpropagation learning rule is presented that compensates for these three non-idealities. The good performance of this learning rule is illustrated by a series of experiments. This algorithm enables the implementation of all-optical multilayer perceptrons where learning occurs under control of a computer.}, dates={August 29--31}, ipdmembership={learning}, }