论文信息 - Incremental Learning With Sample Queries

Incremental Learning With Sample Queries

The classical theory of pattern recognition assumes labeled examples appear according to unknown underlying class conditional probability distributions where the pattern classes are picked randomly in a passive manner according to their a priori probabilities. This paper presents experimental results for an incremental nearest-neighbor learning algorithm which actively selects samples from different pattern classes according to a querying rule as opposed to the a priori probabilities. The amount of improvement of this query-based approach over the passive batch approach depends on the complexity of the Bayes rule.

Joel Ratsaby | Joel Ratsaby

[1] László Györfi,et al. A Probabilistic Theory of Pattern Recognition , 1996, Stochastic Modelling and Applied Probability.

[2] C. G. Hilborn,et al. The Condensed Nearest Neighbor Rule , 1967 .

[3] Joseph O'Rourke,et al. Computational Geometry in C. , 1995 .

[4] Peter E. Hart,et al. The condensed nearest neighbor rule (Corresp.) , 1968, IEEE Trans. Inf. Theory.

[5] M. C. Jones,et al. E. Fix and J.L. Hodges (1951): An Important Contribution to Nonparametric Discriminant Analysis and Density Estimation: Commentary on Fix and Hodges (1951) , 1989 .

[6] G. Gates,et al. The reduced nearest neighbor rule (Corresp.) , 1972, IEEE Trans. Inf. Theory.

[7] G. Gates. The Reduced Nearest Neighbor Rule , 1998 .

[8] Vladimir Vapnik,et al. Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics) , 1982 .

[9] J. O´Rourke,et al. Computational Geometry in C: Arrangements , 1998 .

[10] David A. Cohn,et al. Neural Network Exploration Using Optimal Experiment Design , 1993, NIPS.

[11] Michael Ian Shamos,et al. Computational geometry: an introduction , 1985 .

[12] Ronald L. Rivest,et al. On the sample complexity of pac-learning using random and chosen examples , 1990, Annual Conference Computational Learning Theory.