Communications of the ACM
Learning regular sets from queries and counterexamples
Information and Computation
Inference of finite automata using homing sequences
STOC '89 Proceedings of the twenty-first annual ACM symposium on Theory of computing
COLT '88 Proceedings of the first annual workshop on Computational learning theory
Parallel algorithms for shared-memory machines
Handbook of theoretical computer science (vol. A)
An introduction to parallel algorithms
An introduction to parallel algorithms
The design and analysis of efficient learning algorithms
The design and analysis of efficient learning algorithms
Asking questions to minimize errors
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
A framework for polynomial-time query learnability
Mathematical Systems Theory
Introduction To Automata Theory, Languages, And Computation
Introduction To Automata Theory, Languages, And Computation
Machine Learning
Machine Learning
A Note on the Query Complexity of Learning DFA (Extended Abstract)
ALT '92 Proceedings of the Third Workshop on Algorithmic Learning Theory
Noise-tolerant parallel learning of geometric concepts
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Exact Learning of Formulas in Parallel
Machine Learning
Theoretical Computer Science - Algorithmic learning theory
ALT '98 Proceedings of the 9th International Conference on Algorithmic Learning Theory
A bibliographical study of grammatical inference
Pattern Recognition
Zulu: an interactive learning competition
FSMNLP'09 Proceedings of the 8th international conference on Finite-state methods and natural language processing
Hi-index | 0.00 |
Sequential algorithms given by Alguin (1987) and Schapire (1992) learn deterministic finite automata (dfa) exactly from Membership and Equivalence queries. These algorithms are feasible, in the sense that they take time polynomial in n and m, where n is the number of states of the automaton and m is the length of the longest counterexample to an Equivalence query. This paper studies whether parallelism can lead to substantially more efficient algorithms for the problem. We show that no CRCW PRAM machine using a number of processors polynomial in n and m can identify dfa in o(n/logn) time. Furthermore, this lower bound is tight up to constant factors: we develop a CRCW PRAM learning algorithm that uses polynomially many processors and exactly learns dfa in time O(n/logn).