Fault-tolerant implementation of finite-state automata in recurrent neural networks
US5706400A · kind A · utility
Assignee
Inventors
Key dates
| Filing date | Mar 8, 1995 |
| Grant date | Jan 6, 1998 |
| Priority date | — |
| Expiry date | Mar 8, 2015 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/105
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Any deterministic finite-state automata (DFA) can be implemented in a sparse recurrent neural network (RNN) with second-order weights and sigmoidal discriminant functions. Construction algorithms can be extended to fault-tolerant DFA implementations such that faults in an analog implementation of neurons or weights do not affect the desired network performance. The weights are replicated k times for k-1 fault tolerance. Alternatively, the independent network is replicated 2k+1 times and the majority of the outputs is used for a k fault tolerance. In a further alternative solution, a single network with k.eta. neurons uses a "n choose k"encoding algorithm for k fault tolerance.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.