Abstract
A direct gradient descent learning algorithm of energy function in Hopfield neural networks is proposed. The gradient descent learning is not performed on usual error functions, but the Hopfield energy functions directly. We demonstrate the algorithm by testing it on an analog-to-digital conversion and an associative memory problems.
| Original language | English |
|---|---|
| Pages (from-to) | 252-257 |
| Number of pages | 6 |
| Journal | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences |
| Volume | E79-A |
| Issue number | 2 |
| State | Published - 1996 |
Keywords
- Analog-to-digital conversion
- Associative memory
- Gradient descent learning
- Hopfield model
- Neural networks
ASJC Scopus subject areas
- Signal Processing
- Computer Graphics and Computer-Aided Design
- Electrical and Electronic Engineering
- Applied Mathematics