Neural Computation
May 1992, Vol. 4, No. 3, Pages 406-414
(doi: 10.1162/neco.1992.4.3.406)
Induction of Finite-State Languages Using Second-Order Recurrent Networks
Article PDF (447 KB)
Abstract
Second-order recurrent networks that recognize simple finite state languages over {0,1}* are induced from positive and negative examples. Using the complete gradient of the recurrent network and sufficient training examples to constrain the definition of the language to be induced, solutions are obtained that correctly recognize strings of arbitrary length.