Communications of the ACM
Learning regular sets from queries and counterexamples
Information and Computation
Rational series and their languages
Rational series and their languages
The equivalence problem of multitape finite automata
Theoretical Computer Science
Computational learning theory: survey and selected bibliography
STOC '92 Proceedings of the twenty-fourth annual ACM symposium on Theory of computing
Learning Sat-k-DNF formulas from membership queries
STOC '96 Proceedings of the twenty-eighth annual ACM symposium on Theory of computing
Learning Behaviors of Automata from Multiplicity and Equivalence Queries
SIAM Journal on Computing
Reversal-Bounded Multicounter Machines and Their Decision Problems
Journal of the ACM (JACM)
Inductive Inference: Theory and Methods
ACM Computing Surveys (CSUR)
Automata, Languages, and Machines
Automata, Languages, and Machines
Semirings, Automata and Languages
Semirings, Automata and Languages
Automata: Theoretic Aspects of Formal Power Series
Automata: Theoretic Aspects of Formal Power Series
Machine Learning
Machine Learning
On Learning Programs and Small Depth Circuits
EuroCOLT '97 Proceedings of the Third European Conference on Computational Learning Theory
On the applications of multiplicity automata in learning
FOCS '96 Proceedings of the 37th Annual Symposium on Foundations of Computer Science
Finite automata and their decision problems
IBM Journal of Research and Development
| Hi-index | 0.00 |
We investigate the learning problem of unary output two-tape non deterministic finite automata (unary output 2-tape NFAs) from multiplicity and equivalence queries. Given an alphabet A and a unary alphabet {x}, a unary output 2-tape NFA accepts a subset of A* × {x}*. In [6] Bergadano and Varricchio proved that the behavior of an unknown automaton with multiplicity in a field K (K-automaton) is exactly identifiable when multiplicity and equivalence queries are allowed. In this paper multiplicity automata are used to prove the learnability of unary output 2-tape NFA's. We shall identify the behavior of a unary output 2- tape NFA using an automaton with multiplicity in Krat〈x〉. We provide an algorithm which is polynomial in the size of this automaton.