# Learning from multiple sources of inaccurate data

## Abstract

Most theoretical studies of inductive inference model a situation involving a machine *M* learning its environment *E* on following lines. *M*, placed in *E*, receives data about *E*, and simultaneously conjectures a sequence of hypotheses. *M* is said to learn *E* just in case the sequence of hypotheses conjectured by *M* stabilizes to a final hypothesis which correctly represents *E*.

The above model makes the idealized assumption that the data about *E* that *M* receives is from a *single* and *accurate* source. An argument is made in favor of a more realistic learning model which accounts for data emanating from *multiple* sources, some or all of which may be *inaccurate*. Motivated by this argument, the present paper introduces and theoretically analyzes a number of inference criteria in which a machine is fed data from multiple sources, some of which could be infected with inaccuracies. The main parameters of the investigation are the number of data sources, the number of faulty data sources, and the kind of inaccuracies.

## Keywords

Learning Machine Inductive Inference Inaccurate Data Idealize Assumption Computational Learn Theory## Preview

Unable to display preview. Download preview PDF.

## References

- [Bar74]J. M. Barzdin. Two theorems on the limiting synthesis of functions.
*In Theory of Algorithms and Programs, Latvian State University, Riga*, 210:82–88, 1974. In Russian.Google Scholar - [BB75]L. Blum and M. Blum. Toward a mathematical theory of inductive inference.
*Information and Control*, 28:125–155, 1975.Google Scholar - [Blu67]M. Blum. A machine independent theory of the complexity of recursive functions.
*Journal of the ACM*, 14:322–336, 1967.Google Scholar - [Cas74]J. Case. Periodicity in generations of automata.
*Mathematical Systems Theory*, 8:15–32, 1974.Google Scholar - [CL82]J. Case and C. Lynes. Machine inductive inference and language identification.
*Lecture Notes in Computer Science*, 140:107–115, 1982.Google Scholar - [CS83]J. Case and C. Smith. Comparison of identification criteria for machine inductive inference.
*Theoretical Computer Science*, 25:193–220, 1983.Google Scholar - [FCe90]M. Fulk and J. Case (editors).
*Proceedings of the Third Annual Workshop on Computational Learning Theory*. Morgan Kaufmann Publishers, Inc., August 1990.Google Scholar - [FJ89]M. A. Fulk and S. Jain. Learning in the presence of inaccurate information. In R. Rivest, D. Haussler, and M. K. Warmuth, editors,
*Proceedings of the Second Annual Workshop on Computational Learning Theory, Santa Cruz, California*, pages 175–188. Morgan Kaufmann Publishers, Inc., August 1989.Google Scholar - [Ful85]M. Fulk.
*A Study of Inductive Inference machines*. PhD thesis, SUNY at Buffalo, 1985.Google Scholar - [Gol67]E. M. Gold. Language identification in the limit.
*Information and Control*, 10:447–474, 1967.Google Scholar - [HPe88]D. Haussler and L. Pitt (editors).
*Proceedings of the 1988 Workshop on Computational Learning Theory*. Morgan Kaufmann Publishers, Inc., August 1988.Google Scholar - [Jai90]S. Jain.
*Learning in the Presence of Additional Information and Inaccurate Information*. PhD thesis, University of Rochester, 1990.Google Scholar - [MY78]M. Machtey and P. Young.
*An Introduction to the General Theory of Algorithms*. North Holland, New York, 1978.Google Scholar - [OSW86]D. Osherson, M. Stob, and S. Weinstein.
*Systems that Learn, An Introduction to Learning Theory for Cognitive and Computer Scientists*. MIT Press, Cambridge, Mass., 1986.Google Scholar - [OW82]D. Osherson and S. Weinstein. A note on formal learning theory.
*Cognition*, 11:77–88, 1982.Google Scholar - [Put73]H. Putnam. Reductionism and the nature of psychology.
*Cognition*, 2:131–146, 1973.Google Scholar - [RHWe89]R. Rivest, D. Haussler, and M. K. Warmuth (editors).
*Proceedings of the Second Annual Workshop on Computational Learning Theory*. Morgan Kaufmann Publishers, Inc., August 1989.Google Scholar - [Rog58]H. Rogers. Gödel numberings of partial recursive functions.
*Journal of Symbolic Logic*, 23:331–341, 1958.Google Scholar - [Rog67]H. Rogers.
*Theory of Recursive Functions and Effective Computability*. McGraw Hill, New York, 1967. Reprinted. MIT Press. 1987.Google Scholar - [Smi82]C. Smith. The power of pluralism for automatic program synthesis.
*Journal of the ACM*, 29:1144–1165, 1982.Google Scholar - [Sol64a]R. J. Solomonoff. A formal theory of inductive inference, Part I.
*Information and Control*, 7:1–22, 1964.Google Scholar - [Sol64b]R. J. Solomonoff. A formal theory of inductive inference, Part II.
*Information and Control*, 7:224–254, 1964.Google Scholar - [SR86]G. Schäfer-Richter. Some results in the theory of effective program synthesis — learning by defective information.
*Lecture Notes in Computer Science*, 215:219–225, 1986.Google Scholar - [VWe91]L. G. Valiant and M. K. Warmuth (editors).
*Proceedings of the Fourth Annual Workshop on Computational Learning Theory*. Morgan Kaufmann Publishers, Inc., August 1991.Google Scholar