Constrained Second-Order Recurrent Networks for Finite-State Automata Induction

This paper presents an improved training algorithm for second-order dynamicalrecurrent networks applied to the problem of finite-state automata(FSA) induction. Second-order networks allow for a natural encodingof finite-state automata in which each second-order connectionweight corresponds to one transition in a finite-state automaton. In practice,however, when trained using gradient descent, these networks seldomassume this type of encoding and sophisticated algorithms must be...