Learning Stochastic Finite Automata

Abstract. Stochastic deterministic finite automata have been introduced and are used in a variety of settings. We report here a number of results concerning the learnability of these finite state machines. In the setting of identification in the limit with probability one, we prove that stochastic deterministic finite automata cannot be identified from only a polynomial quantity of data. If concerned with approximation results, they become Pac-learnable if the L∞ norm is used. We also investigate queries that are sufficient for the class to be learnable.

• Type: Conference
• Year: 2004
• Where: ICGI
• Authors: Colin de la Higuera, José Oncina
• Keywords: Deterministic finite Automata, ICGI 2004, Natural Language Processing, Stochastic, finite State Machines