DS 1998: Discovey Science pp 60-71 | Cite as
Random Case Analysis of Inductive Learning Algorithms
Abstract
In machine learning, it is important to reduce computational time to analyze learning algorithms. Some researchers have attempted to understand learning algorithms by experimenting them on a variety of domains. Others have presented theoretical methods of learning algorithm by using approximately mathematical model. The mathematical model has some deficiency that, if the model is too simplified, it may lose the essential behavior of the original algorithm. Furthermore, experimental analyses are based only on informal analyses of the learning task, whereas theoretical analyses address the worst case. Therefore, the results of theoretical analyses are quite different from empirical results. In our framework, called random case analysis, we adopt the idea of randomized algorithms. By using random case analysis, it can predict various aspects of learning algorithm’s behavior, and require less computational time than the other theoretical analyses. Furthermore, we can easily apply our framework to practical learning algorithms
Preview
Unable to display preview. Download preview PDF.
References
- 1.Aha, D.W.: Case-Based Learning Algorithms, Proc. of Case-Based Reasoning Workshop, pp.147–158 (1991).Google Scholar
- 2.Bruner, J. S., Goodnow, J. J. and Austin, G. A.: A Study of Thinking, Wiley (1956).Google Scholar
- 3.Buntine, W.: A Critique of the Valiant Model, Proc. of the 11th IJCAI, pp.837–842 (1989).Google Scholar
- 4.Haussler, D.: Probably Approximately Correct Learning, Proc. of the 8th AAAI, pp.1101–1108 (1990).Google Scholar
- 5.Iba, W. and Langley, P.: Induction of One-Level Decision Trees, Proc. of the 9th International Workshop on Machine Learning, pp.233–240 (1992).Google Scholar
- 6.Karp, R. M.: An Introduction to Randomized Algorithms, Discrete Applied Mathematics, Vol.34, pp.165–201 (1991).MATHCrossRefMathSciNetGoogle Scholar
- 7.Langley, P., Iba, W. and Thompson, K.: An Analysis of Bayesian Classi.ers, Proc. of the 10th AAAI, pp.223–228 (1992).Google Scholar
- 8.Langley, P. and Iba, W.: Average-Case Analysis of a Nearest Neighbor Algorithm, Proc. of the 13th IJCAI, pp.889–894 (1993).Google Scholar
- 9.Murphy, P. M. and Aha, D. W.: UCI Repository of Machine Learning Databases, Technical report, University of California, Department of Information and Computer Science, Irvine (1992).Google Scholar
- 10.Pazzani, M. J. and Sarett, W.: Average Case Analysis of Conjunctive Learning Algorithm, Proc. of the 7th International Conference on Machine Learning, pp.339–347 (1990).Google Scholar
- 11.Quinlan, J. R.: Induction of Decision Trees, Machine Learning, Vol.1, pp.81–106 (1986).Google Scholar
- 12.Quinlan, J. R.: C4.5: Programs for Machine Learning, Morgan Kaufmann (1993).Google Scholar
- 13.Raghaven, P.: Lecture Notes on Randomized Algorithms, Research report RC 15340, IBM (1990).Google Scholar
- 14.Sakamoto, T. and Uehara, K.: Induction of N-Level Decision Trees, Trans. of IPSJ, Vol.38, No.3, pp.419–428 (1997, in Japanese).Google Scholar
- 15.Shi, Z.: Principles of Machine Learning, International Academic Publishers (1992).Google Scholar