Patent · US Expired

Fault-tolerant implementation of finite-state automata in recurrent neural networks

US5706400A · kind A · utility

8Cited by
1References
7Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 8, 1995
Grant dateJan 6, 1998
Priority date
Expiry dateMar 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.