DS 1998: Discovey Science pp 72-83 | Cite as
On Variants of Iterative Learning
Abstract
Within the present paper, we investigate the principal learning capabilities of iterative learners in some more details. The general scenario of iterative learning is as follows. An iterative learner successively takes as input one element of a text (an informant) of a target concept as well as its previously made hypothesis, and outputs a new hypothesis about the target concept. The sequence of hypotheses has to converge to a hypothesis correctly describing the target concept
We study the following variants of this basic scenario. First, we consider the case that an iterative learner has to learn on redundant texts or informants, only. A text (an informant) is redundant, if it contains every data item infinitely many times. This approach guarantees that relevant information is, in principle, accessible at any time in the learning process. Second, we study a version of iterative learning, where an iterative learner is supposed to learn independent on the choice of the initial hypothesis. In contrast, in the basic scenario of iterative inference, it is assumed that the initial hypothesis is the same for every learning task which allows certain coding tricks
We compare the learning capabilities of all models of iterative learning from text and informant, respectively, to one another as well as to finite inference, conservative identification, and learning in the limit from text and informant, respectively
Keywords
Initial Hypothesis Concept Class Iterative Learning Positive Data Target ConceptPreview
Unable to display preview. Download preview PDF.
References
- 1.Angluin, D., Inductive inference of formal languages from positive data, Information and Control 45, 117–135, 1980.MATHCrossRefMathSciNetGoogle Scholar
- 2.Blum, M., A machine independent theory of the complexity of recursive functions, Journal of the ACM 14, 322–336, 1967.MATHCrossRefMathSciNetGoogle Scholar
- 3.Gold, E.M., Language identification in the limit, Information and Control 10, 447–474, 1967.CrossRefMATHGoogle Scholar
- 4.Hopcroft, J.E., and Ullman, J.D., “Formal Languages and their Relation to Automata”, Addison-Wesley, 1969.Google Scholar
- 5.Kinber, E., and Stephan, F., Language learning from texts: Mind changes, limited memory and monotonicity, in “Proceedings 8th Annual ACM Conference on Computational Learning Theory,” pp. 182–189, ACM Press, 1995.Google Scholar
- 6.Kolodner, J.K., An introduction to case-based reasoning. Artificial Intelligence Review 6, 3–34, 1992.CrossRefGoogle Scholar
- 7.Lange, S., and Zeugmann, T., Types of monotonicl anguage learning and their characterization, in “Proceedings 5th Annual ACM Workshop on Computational Learning Theory,” pp. 377–390, ACM Press, 1992.Google Scholar
- 8.Lange, S., and Zeugmann, T., Language learning in dependence on the space of hypotheses, in “Proceedings 6th Annual ACM Conference on Computational Learning Theory,” pp. 127–136, ACM Press, 1993.Google Scholar
- 9.Lange, S., and Zeugmann, T., Incremental learning from positive data, Journal of Computer and System Sciences 53, 88–103, 1996.MATHCrossRefMathSciNetGoogle Scholar
- 10.Lange, S., and Zeugmann, T., Set-driven and rearrangement-independent learning of recursive languages, Mathematical Systems Theory 29, 599–634, 1996.MATHMathSciNetGoogle Scholar
- 11.Rivest, R., Learning decision lists, Machine Learning 2, 229–246, 1987.MathSciNetGoogle Scholar
- 12.Valiant, L.G., A theory of the learnable, Communications of the ACM 27, 1134–1142, 1984.MATHCrossRefGoogle Scholar
- 13.Wexler, K., and Culicover, P., “Formal Principles of Language Acquisition”, MIT Press, 1980.Google Scholar
- 14.Wiehagen, R., Limes-Erkennung rekursiver Funktionen durch spezielle Strategien, Journal of Information Processing and Cybernetics (EIK) 12, 93–99, 1976.Google Scholar
- 15.Zeugmann, T., and Lange, S., A guided tour across the boundaries of learning recursive languages, in “AlgorithmicL earning for Knowledge-Based Systems,” Lecture Notes in Artificial Intelligence, Vol. 961, pp. 193–262, Springer-Verlag, 1995.Google Scholar