In this monograph, the authors introduce a novel fuzzy rule-base, referred to as the Fuzzy All-permutations Rule-Base (FARB). They show that inferring the FARB, using standard tools from fuzzy logic theory, yields an input-output map that is mathematically equivalent to that of an artificial neural network. Conversely, every standard artificial neural network has an equivalent FARB. The FARB-ANN equivalence integrates the merits of symbolic fuzzy rule-bases and sub-symbolic artificial neural networks, and yields a new approach for knowledge-based neurocomputing in artificial neural networks.
| Autorius: | Michael Margaliot, Eyal Kolman, |
| Serija: | Studies in Fuzziness and Soft Computing |
| Leidėjas: | Springer Berlin Heidelberg |
| Išleidimo metai: | 2010 |
| Knygos puslapių skaičius: | 116 |
| ISBN-10: | 3642099858 |
| ISBN-13: | 9783642099854 |
| Formatas: | Knyga minkštu viršeliu |
| Kalba: | Anglų |
| Žanras: | Maths for engineers |
Parašykite atsiliepimą apie „Knowledge-Based Neurocomputing: A Fuzzy Logic Approach“
