Inference of stochastic regular languages through simple recurrent networks
M.A. Castana, Enrique Vidal, Francisco Casacuberta · 1993
Grammatical inference has been recently approached through artificial neural networks. Recurrent connectionist architectures were trained to accept or reject strings belonging to a number of specific regular languages, or to predict the possible successor(s) for each character in the string. On the other hand, for static (non-string) data, M.D. Richard et al. (1991), showed that a nonrecurrent architecture can estimate Bayesian a posteriori probabilities. The authors show empirical evidence supporting this statement which also seems to be verified when simple recurrent networks (SRNs) are used to estimate probabilities of stochastic regular languages. >