|
|
|
|
| LEADER |
01059 am a22001933u 4500 |
| 001 |
259797 |
| 042 |
|
|
|a dc
|
| 100 |
1 |
0 |
|a Pignon, D.
|e author
|
| 700 |
1 |
0 |
|a Parmiter, P.J.M.
|e author
|
| 700 |
1 |
0 |
|a Slack, J.K.
|e author
|
| 700 |
1 |
0 |
|a Hands, M.A.
|e author
|
| 700 |
1 |
0 |
|a Hall, T.J.
|e author
|
| 700 |
1 |
0 |
|a Daalen, M.
|e author
|
| 700 |
1 |
0 |
|a Shawe-Taylor, J.
|e author
|
| 245 |
0 |
0 |
|a Sigmoid Neural Transfer Function Realised by Percolation
|
| 260 |
|
|
|c 1996-02.
|
| 856 |
|
|
|z Get fulltext
|u https://eprints.soton.ac.uk/259797/1/OpticsLettersVol21No3Feb96.pdf
|
| 520 |
|
|
|a An experiment using the phenomenon of percolation has been conducted to demonstrate the implementation of neural functionality (summing and sigmoid transfer). A simple analog approximation to digital percolation is implemented. The device consists of a piece of amorphous silicon with stochastic bit-stream optical inputs, in which a current percolating from one end to the other defines the neuron output, also in the form of a stochastic bit stream. Preliminary experimental results are presented.
|
| 655 |
7 |
|
|a Article
|
