Training the neocognitron network using design of experiments
| Autor: | Ming Yeong Teo, Siang Kok Sim |
|---|---|
| Rok vydání: | 1995 |
| Předmět: |
Structure (mathematical logic)
Engineering General Computer Science Artificial neural network business.industry Design of experiments General Engineering Neocognitron Pattern recognition Machine learning computer.software_genre Set (abstract data type) Pattern recognition (psychology) Artificial intelligence Orthogonal array business Scaling computer |
| Zdroj: | Artificial Intelligence in Engineering. 9:85-94 |
| ISSN: | 0954-1810 |
| DOI: | 10.1016/0954-1810(95)95752-r |
| Popis: | Neocognitron is a hierarchically structured multi-layer neural network that is recognised for its ability to tolerate scaling and rotational effects of the input patterns. However, there are many parameters that describe the hierarchical multi-layer structure of the network which must be adjusted properly for the network to recognise a set of patterns to allow for their scaling and rotational effects. The methodology utilises an orthogonal array to determine combination of values of the various parameters, instead of all the possible combinations, thus greatly reducing the number of trials required to arrive at the optimum values. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect