In this paper we outline some of the changes needed to implement multilayer feed-forward neural networks using the demonstrator hardware which was based on around an array of vertical cavity surface emitting lasers. Network simulations show that the neural network demonstrator hardware can be used to implement two different classes of feed-forward network, the multilayer perceptron (MLP) and radial basis function (RBF) networks. In both cases, the actual training of the networks is performed offline using hardware simulations and the weighted interconnections between neurons are fixed before application to the optoelectronic hardware.
Optoelectronic neural networks: mapping multilayer architectures on to an optoelectronic demonstrator
2003-01-01
87986 byte
Conference paper
Electronic Resource
English
Modular architectures for optoelectronic multistage interconnection networks
British Library Online Contents | 1994
|Backpropagation Learning Using Positive Weights for Multilayer Optoelectronic Neural Networks
British Library Conference Proceedings | 1996
|Interconnection theory and optoelectronic computing architectures
British Library Conference Proceedings | 1995
|