Overcoming Inaccuracies in Optical Multilayer Perceptrons
| Type of publication: | Conference paper |
| Citation: | Moerland-96.3 |
| 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. |
| Userfields: | dates={August 29--31}, ipdmembership={learning}, |
| Keywords: | activation function, liquid crystal light valve (LCLV), non-negative neural networks, optical multilayer perceptron, weight discretization |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|