Abstract
The shortcomings of automatic learning in neural networks can be overcome by incorporating features of the problem into the weight space. We teach a multi-layer perceptron to recognize hand-printed characters by using a multi-scale method. This leads to better performance for learning rates and for generalization than direct use of back-propagation.
Original language | English (US) |
---|---|
Pages (from-to) | 503-509 |
Number of pages | 7 |
Journal | Biological Cybernetics |
Volume | 62 |
Issue number | 6 |
DOIs | |
State | Published - Apr 1990 |
All Science Journal Classification (ASJC) codes
- Biotechnology
- General Computer Science