|
| << previous | next >> |
Journal description
All volumes of the corresponding journal
All issues of the corresponding volume
All articles of the corresponding issues
Details for article 34 of 46 found articles
| Title: |
Probabilistic Bit Stream Neural Chip: Theory |
| Author: |
Shawe-Taylor, John Jeavons, Pete Van Daalen, Max |
| Appeared in: |
Connection science |
| Paging: | Volume 3 (1991) nr. 3 pages 317-328 |
| Year: |
1991 |
| Contents: |
A design for a neural network chip is proposed using probabilistic bit streams to represent real values. This paper analyzes the performance of the proposed neurons in this design and demonstrates that very simple operations can be used to obtain the desired functionality. It is also shown that a suitable 'activation function' for neurons of this type can be obtained using the interaction of two probability distributions. Finally, the paper introduces a variant of the back-propagation learning algorithm which involves computing the derivatives of the output with respect to individual weights in a network of such units. |
| Publisher: |
Taylor & Francis |
| Source file: |
Elektronische Wetenschappelijke Tijdschriften |
Details for article 34 of 46 found articles
| << previous | next >> |