Learning from Positive Data and Negative Counterexamples: A Survey
- 630 Downloads
The article presents state of the art on learning languages in the limit from full positive data and negative counterexamples to overextending conjectures. In the main model, the learner can store in its long-term memory all data seen so far. Variants of this model are considered where the learner always gets least counterexamples, or counterexamples bounded by the maximal size of positive data seen. All these variants are also considered for the model, where the learner does not have long-term memory, but can use the last conjecture. Capabilities, properties, and relationships between these models (and some other variations) are surveyed. Also, a variant of the main model restricted to learning classes definable by finite automata by learners definable by finite automata is considered.
KeywordsTarget Language Recursive Function Finite Automaton Iterative Learning Positive Data
Unable to display preview. Download preview PDF.
- [Bar74]Bārzdiņš, J.: Two theorems on the limiting synthesis of functions. In: Theory of Algorithms and Programs, vol. 1, pp. 82–88. Latvian State University (1974). In RussianGoogle Scholar
- [BH70]Brown, R., Hanlon, C.: Derivational complexity and the order of acquisition in child speech. In: Hayes, J.R. (ed.) Cognition and the Development of Language, Wiley (1970)Google Scholar
- [JKS14]Jain, S., Kinber, E., Stephan, F.: Automatic learning from positive data and negative counterexamples (2014). ManuscriptGoogle Scholar
- [LZ06]Li, Y., Zhang, W.: Simplify support vector machines by iterative learning. Neural Processsing Information - Letters and Reviews 10(1), 11–17 (2006)Google Scholar
- [OSW86]Osherson, D., Stob, M., Weinstein, S.: Systems that Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists. MIT Press (1986)Google Scholar
- [Rog67]Rogers, H.: Theory of Recursive Functions and Effective Computability. McGraw-Hill (1967). Reprinted by MIT Press in 1987Google Scholar
- [Shi86]Shinohara, T.: Studies on Inductive Inference from Positive Data. PhD thesis, Kyushu University, Kyushu, Japan (1986)Google Scholar
- [WC80]Wexler, K., Culicover, P.: Formal Principles of Language Acquisition. MIT Press (1980)Google Scholar