Deterministic encoding of fuzzy finite state automata in continuous recurrent neural networks
US5943659A · kind A · utility
24Cited by
5References
4Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Oct 3, 1995 |
| Grant date | Aug 24, 1999 |
| Priority date | — |
| Expiry date | Oct 3, 2015 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG05B13/0285
- WIPO fieldControl
- WIPO sectorInstruments
Abstract
Based on the encoding of deterministic finite-state automata (DFA) in discrete-time, second-order recurrent neural networks, an algorithm constructs an augmented recurrent neural network that encodes a FFA and recognizes a given fuzzy regular language with arbitrary accuracy.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.