Abstract
Learning general concepts in imperfect environments is difficult since training instances often include noisy data, inconclusive data, incomplete data, unknown attributes, unknown attribute values and other barriers to effective learning. It is well known that people can learn effectively in imperfect environments, and can manage to process very large amounts of data. Imitating human learning behavior therefore provides a useful model for machine learning in real-world applications. This paper proposes a new, more effective way to represent imperfect training instances and rules, and based on the new representation, a Human-Like Learning (HULL) algorithm for incrementally learning concepts well in imperfect training environments. Several examples are given to make the algorithm clearer. Finally, experimental results are presented that show the proposed learning algorithm works well in imperfect learning environments.
Article PDF
Similar content being viewed by others
References
D.W. Aha and D. Kibler (1989), ‘Noise-tolerant instance-based learning algorithm’, International Joint Conference on Artificial Intelligence, pp. 794–799, Detroit, Michigan, USA.
D.Angluin (1988), ‘Learning from noisy examples’, Machine Learning 2 pp. 343–370.
A.Baddeley (1990), Human Memory Theory and Practice, Allyn and Bacon, Boston, USA.
J.Cendrowska (1987), PRISM: An algorithm for inducing modular rules’, International Journal of Man-Machine Studies 27, pp. 349–370.
M.Cole and B.Means (1981), Comparative Studies of How People Think: An Introduction, Harvard University Press, Cambridge.
R. Dreistadt (1968), ‘An analysis of the use of analogies and metaphors in science’, The Journal of Psychology, pp. 97–116.
J.F.Hall (1989), Learning and Memory, Ed. 2nd, Allyn and Bacon, Boston, USA.
E.R.Hilgard and G.H.Bower (1975), Theories of Learning, Ed. 4th, Stanford Press, CA.
T.P. Hong (1992), A Study of Parallel Processing and Noise Management on Machine Learning, Ph.D. Thesis, National Chiao Tung University, Hsinchu, Taiwan, R.O.C.
T.P.Hong and S.S.Tseng (1994), ‘Learning concepts in parallel based upon the strategy of version space’, IEEE Transactions on Knowledge and Data Engineering 6–6, pp. 857–867.
G.J. Hwang and S.S. Tseng (1990), ‘Building a multi-purpose medical system under uncertain and incomplete environment’, The Third IEEE Symposium on Computer-Based Medical Systems, pp. 321–328, Chapel Hill, N.C.
R. Jones (1989), ‘Learning to retrieve useful information for problem solving’, Proceedings of the Sixth International Workshop on Machine Learning, Ithaca, New York, pp. 188–190.
Y.Kodratoff and R.S.Michalski (1990), Machine Learning: An Artificial Intelligence Approach, Vol. 3, Toiga, Palo Alto, CA.
Y.Kodratoff, M.Manago, and J.Blythe (1987), ‘Generalization and noise’, International Journal of Man-Machine Studies 27, pp. 181–204.
S. Markovitch and P.D. Scott (1988), ‘The Role of Forgetting in Learning’, Proceedings of the Fifth International Conference on Machine Learning, Ann Arbor, MI, pp. 459–465.
R.S.Michalski, J.G.Carbonell and T.M.Mitchell (1983), Machine Learning: An Artificial Intelligence Approach, Vol. 1, Toiga, Palo Alto, CA.
R.S.Michalski, J.G.Carbonell, and T.M.Mitchell (1984), Machine Learning: An Artificial Intelligence Approach, Vol. 2, Toiga, Palo Alto, CA.
D.A.Norman (1991), ‘Approaches to the study of intelligence’, Artificial Intelligence 49 pp. 327–346.
A.L.Ralescu and J.F.Baldwin (1989), ‘Concept learning from examples and counter examples’, International Journal of Man-Machine Studies, 30, pp. 329–354.
J.R. Quinlan (1989), ‘Unknown attribute values in induction’, Proceedings of the Sixth International Workshop on Machine Learning, pp. 164–168, Ithaca, New York.
J.R.Quinlan (1983), ‘Learning efficient classification procedures and their application to chess end games’, Machine Learning: An Artificial Intelligence Approach, Vol. 1. Toiga, Palo Alto, CA, pp. 463–482.
P.D. Scott and S. Markovitch (1989), ‘Uncertainty based selection of learning experiences’, Proceedings of the Sixth International Workshop on Machine Learning, Ithaca, New York, pp. 358–361.
J.C. Schlimmer, R.H. Granger, J.R. (1986), ‘Incremental learning from noisy data’, Machine Learning 1, pp. 317–354.
S. Spangler, U.M. Fayyad and Ramasamy Uthurusamy (1989), ‘Induction of decision trees from inconclusive data’, Proceedings of the Sixth International Workshop on Machine Learning, Ithaca, New York, pp. 146–150.
M. Tambe and A. Newell (1988), ‘Some chunks are expensive’, Proceedings of the Fifth International Conference on Machine Learning, Ann Arbor, MI. pp. 451–458.
K. VanLehn (1989), ‘Discovering problem solving strategies: What humans do and machines don't (yet)’, Proceedings of the Sixth International Workshop on Machine Learning, Ithaca, New York, pp. 215–217.
C.H. Wang and S.S. Tseng (1990), ‘A brain tumor diagnostic system with automatic learning abilities’, Proceedings of the Third IEEE Symposium on Computer-Based Medical Systems, pp. 313–320, Chapel Hill, N.C.
P.G.Zimbardo (1980), Essentials of Psychology and Life, Ed. 10th, Scott, Foresman and Company Press, Dallas, Tex.
P.G.Zimbardo (1990), Psychology and Life, Ed. 12th, Scott, Foresman and Company Press, Dallas, Tex.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chang, KC., Hong, TP. & Tseng, SS. Machine learning by imitating human learning. Mind Mach 6, 203–228 (1996). https://doi.org/10.1007/BF00391286
Issue Date:
DOI: https://doi.org/10.1007/BF00391286