Discrete All-Positive Multilayer Perceptrons for Optical Implementation
| Type of publication: | Journal paper |
| Citation: | Moerland-98.1 |
| Journal: | Optical Engineering |
| Volume: | 37 |
| Number: | 4 |
| Year: | 1998 |
| Month: | 4 |
| Note: | (IDIAP-RR 97-02) |
| 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. |
| Userfields: | ipdinar={1997}, ipdmembership={learning}, |
| Keywords: | |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
