Learning regular sets from queries and counterexamples
Information and Computation
Approximate counting, uniform generation and rapidly mixing Markov chains
Information and Computation
Negative Results for Equivalence Queries
Machine Learning
On the learnability of finite automata
COLT '88 Proceedings of the first annual workshop on Computational learning theory
Learning regular languages from counterexamples
COLT '88 Proceedings of the first annual workshop on Computational learning theory
On learning from queries and counterexamples in the presence of noise
Information Processing Letters
Efficient learning of typical finite automata from random walks
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Cryptographic limitations on learning Boolean formulae and finite automata
Journal of the ACM (JACM)
Diversity-based inference of finite automata
Journal of the ACM (JACM)
Inference of finite automata using homing sequences
Information and Computation
Learning from a consistently ignorant teacher
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Learning behaviors of automata from multiplicity and equivalence queries
CIAC '94 Proceedings of the second Italian conference on Algorithms and complexity
Optimality and domination in repeated games with bounded players
STOC '94 Proceedings of the twenty-sixth annual ACM symposium on Theory of computing
Learning Fallible Deterministic Finite Automata
Machine Learning - Special issue on COLT '93
Randomized algorithms
On learning bounded-width branching programs
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Inductive Inference: Theory and Methods
ACM Computing Surveys (CSUR)
Switching and Finite Automata Theory: Computer Science Series
Switching and Finite Automata Theory: Computer Science Series
Machine Learning
Efficient algorithms for learning to play repeated games against computationally bounded adversaries
FOCS '95 Proceedings of the 36th Annual Symposium on Foundations of Computer Science
The power of a pebble: exploring and mapping directed graphs
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
The power of a pebble: exploring and mapping directed graphs
Information and Computation
| Hi-index | 0.00 |
We present algorithms for exactly learning unknown environments thatcan be described by deterministic finite automata. The learnerperforms a walk on the target automaton, where at each step itobserves the output of the state it is at, and chooses a labeled edgeto traverse to the next state. The learner has no means of a reset,and does not have access to a teacher that answers equivalencequeries and gives the learner counterexamples to its hypotheses. Wepresent two algorithms: The first is for the case in which theoutputs observed by the learner are always correct, and the second isfor the case in which the outputs might be corrupted by randomnoise. The running times of both algorithms are polynomial in thecover time of the underlying graph of the target automaton.