Definition
Inductive inference is a theoretical framework to model learning in the limit. The typical scenario is that the learner reads successively datum d0, d1, d2, … about a concept and outputs in parallel hypotheses e0, e1, e2, … such that each hypothesis e n is based on the preceding data d0, d1, …, dn−1. The hypotheses are expected to converge to a description for the data observed; here the constraints on how the convergence has to happen depend on the learning paradigm considered. In the most basic case, almost all e n have to be the same correct index e, which correctly explains the target concept. The learner might have some preknowledge of what the concept might be, that is, there is some class \(\mathcal{C}\) of possible target concepts – the learner has only to find out which of the concepts in \(\mathcal{C}\) is the target concept; on the other hand, the learner has to be able to learn every concept which is in the class \(\mathcal{C}\).
Detail
The above given scenario...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Recommended Reading
Angluin D (1980) Inductive inference of formal languages from positive data. Inf Control 45:117–135
Bārzdiņš J (1974a) Inductive inference of automata, functions and programs. In: Proceedings of the international congress of mathematics, Vancouver, pp 771–776
Bārzdiņš J (1974b) Two theorems on the limiting synthesis of functions. In: Theory of algorithms and programs, vol 1. Latvian State University, Riga, pp 82–88 (In Russian)
Blum L, Blum M (1975) Toward a mathematical theory of inductive inference. Inf Control 28:125–155
Case J (1999) The power of vacillation in language learning. SIAM J Comput 28:1941–1969
Case J, Lynes C (1982) Machine inductive inference and language identification. In: Nielsen M, Schmidt EM (eds) Proceedings of the 9th international colloquium on automata, languages and programming. Lecture notes in computer science, vol 140. Springer, Heidelberg, pp 107–115
Case J, Smith C (1983) Comparison of identification criteria for machine inductive inference. Theor Comput Sci 25:193–220
Fulk M (1990) Prudence and other conditions on formal language learning. Inf Comput 85:1–11
Gold EM (1967) Language identification in the limit. Inf Control 10:447–474
Jain S, Osherson D, Royer J, Sharma A (1999) Systems that learn: an introduction to learning theory, 2nd edn. MIT Press, Cambridge
Jain S, Stephan F, Ye N (2008) Prescribed learning of indexed families. Fundam Inf 83:159–175
Jantke KP (1991) Monotonic and non-monotonic inductive inference. New Gener Comput 8:349–360
Jantke KP, Beick H-R (1981) Combining postulates of naturalness in inductive inference. J Inf Process Cybern (EIK) 17:465–484
Lange S, Zeugmann T (1993) Language learning in dependence on the space of hypotheses. In: Proceedings of the sixth annual conference on computational learning theory, Santa Cruz, pp 127–136
Lange S, Zeugmann T, Kapur S (1992) Class preserving monotonic language learning. Technical report 14/92, GOSLER-Report, FB Mathematik und Informatik, TH Leipzig
Lange S, Zeugmann T, Zilles S (2008). Learning indexed families of recursive languages from positive data: a survey. Theor Comput Sci 397: 194–232
Minicozzi E (1976) Some natural properties of strong identification in inductive inference. Theor Comput Sci 2:345–360
Osherson D, Weinstein S (1982) Criteria of language learning. Inf Control 52:123–138
Osherson D, Stob M, Weinstein S (1986) Systems that learn, an introduction to learning theory for cognitive and computer scientists. Bradford–The MIT Press, Cambridge
Sharma A (1998) A note on batch and incremental learnability. J Comput Syst Sci 56:272–276
Wiehagen R (1990) A thesis in inductive inference. In: Dix J, Jantke K, Schmitt P (eds) Nonmonotonic and inductive logic, 1st international workshop. Lecture notes in artificial intelligence, vol 543. Springer, Berlin, pp 184–207
Wiehagen R, Liepe W (1976) Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen. J Inf Process Cybern (EIK) 12:421–438
Wiehagen R, Zeugmann T (1995) Learning and consistency. In: Jantke KP, Lange S (eds) Algorithmic learning for knowledge-based systems (GOSLER), final report. Lecture notes in artificial intelligence, vol 961. Springer, Heidelberg, pp 1–24
Acknowledgements
Sanjay Jain was supported in part by NUS grant numbers C252-000-087-001, R146-000-181-112, R252-000-534-112. Frank Stephen was supported in part by NUS grant numbers R146-000-181-112, R252-000-534-112.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media New York
About this entry
Cite this entry
Jain, S., Stephan, F. (2017). Inductive Inference. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1_134
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7687-1_134
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-7685-7
Online ISBN: 978-1-4899-7687-1
eBook Packages: Computer ScienceReference Module Computer Science and Engineering