Second-Order Recurrent Neural Networks Can Learn Regular Grammars from Noisy Strings

@inproceedings{Carrasco1995SecondOrderRN,
  title={Second-Order Recurrent Neural Networks Can Learn Regular Grammars from Noisy Strings},
  author={Rafael C. Carrasco and Mikel L. Forcada},
  booktitle={IWANN},
  year={1995}
}
Recent work has shown that second-order recurrent neural networks (2ORNNs) may be used to infer deterministic nite automata (DFA) when trained with positive and negative string examples. This paper shows that 2ORNN can also learn DFA from samples consisting of pairs (W; W) where W is a noisy string of input vectors describing the degree of resemblance of every input to the symbols in the alphabet , and W is the degree of acceptance of the noisy string, computed with a DFA whose behavior has… CONTINUE READING
View Paper

From This Paper

Topics from this paper.

Explore Further: Topics Discussed in This Paper