Correlated patterns in non-monotonic graded-response perceptrons
| Autor: | Désiré Bollé, Toni Verbeiren |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 1999 |
| Předmět: |
Artificial neural network
Statistical Mechanics (cond-mat.stat-mech) business.industry Computer Science::Neural and Evolutionary Computation Structure (category theory) FOS: Physical sciences Pattern recognition Disordered Systems and Neural Networks (cond-mat.dis-nn) Condensed Matter - Disordered Systems and Neural Networks Perceptron Computer Science::Computer Vision and Pattern Recognition Statistics Symmetry breaking Artificial intelligence Overall performance business Condensed Matter - Statistical Mechanics Mathematics |
| Popis: | The optimal capacity of graded-response perceptrons storing biased and spatially correlated patterns with non-monotonic input-output relations is studied. It is shown that only the structure of the output patterns is important for the overall performance of the perceptrons. 4 pages, 4 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|