Parallel Learning of Automatic Classes of Languages
We introduce and explore a model for parallel learning of families of languages computable by finite automata. In this model, an algorithmic or automatic learner takes on n different input languages and identifies at least m of them correctly. For finite parallel learning, for large enough families, we establish a full characterization of learnability in terms of characteristic samples of languages. Based on this characterization, we show that it is the difference n − m, the number of languages which are potentially not identified, which is crucial. Similar results are obtained also for parallel learning in the limit. We consider also parallel finite learnability by finite automata and obtain some partial results. A number of problems for automatic variant of parallel learning remain open.
KeywordsCharacteristic Sample Bipartite Graph Inductive Inference Maximal Chain Maximum Match
Unable to display preview. Download preview PDF.
- [BG00]Blumensath, A., Grädel, E.: Automatic structures. In: 15th Annual IEEE Symposium on Logic in Computer Science (LICS), pp. 51–62. IEEE Computer Society (2000)Google Scholar
- [JORS99]Jain, S., Osherson, D., Royer, J., Sharma, A.: Systems that Learn: An Introduction to Learning Theory, 2nd edn. MIT Press, Cambridge (1999)Google Scholar
- [Kin76]Kinber, E.: Frequency computations in finite automata. Kibernetika 2, 7–15 (1976) (in Russian); English translation in Cybernetics 12, 179–187Google Scholar
- [LZ93]Lange, S., Zeugmann, T.: Language learning in dependence on the space of hypotheses. In: Proceedings of the Sixth Annual Conference on Computational Learning Theory, pp. 127–136. ACM Press (1993)Google Scholar
- [PS98]Papadimitriou, C.H.S., Steiglitz, K.: Combinatorial Optimization: Algorithms and Complexity. Dover (1998)Google Scholar
- [Ros60]Rose, G.: An extended notion of computability. Abstracts of International Congress for Logic, Methodology and Philosophy of Science, p. 14 (1960)Google Scholar
- [Tra64]Trakhtenbrot, B.: On the frequency of computation of functions. Algebra i Logika 2, 25–32 (1964)Google Scholar