摘要: Littlestone's WINNOW algorithm for learning disjunctions of Boolean attributes where most are irrelevant is one the fundamental results in theory. Because importance WINNOW, it natural to try extending learn features (i.e., concepts). In doing so, we may generalize some earlier applications WINNow. this paper, extend WiNNow k-disjunctions indicator-feature pairs each pair a conjunction attribute and feature (concept) from certain type class. (When all always set 1, then concept class features.)
springer.com
sci-hub.st 参考文章(19)
Wolfgang Maass, Manfred K. Warmuth, Efficient Learning with Virtual Threshold Gates Machine Learning Proceedings 1995. pp. 378- 386 ,(1995) , 10.1016/B978-1-55860-377-6.50054-2
Foued Ameur, A space-bounded learning algorithm for axis-parallel rectangles european conference on computational learning theory. pp. 313- 321 ,(1995) , 10.1007/3-540-59119-2_187
David Helmbold, Stephen Kwek, Leonard Pitt, Learning When to Trust Which Experts european conference on computational learning theory. pp. 134- 149 ,(1997) , 10.1007/3-540-62685-9_12
Andrew R. Golding, Dan Roth, Applying Winnow to Context-Sensitive Spelling Correction international conference on machine learning. pp. 182- 190 ,(1996)
Nader H. Bshouty, Sally A. Goldman, H. David Mathias, Noise-tolerant parallel learning of geometric concepts conference on learning theory. pp. 345- 352 ,(1995) , 10.1145/225298.225340
Nicholas Littlestone, Redundant noisy attributes, attribute errors, and linear-threshold learning using winnow conference on learning theory. pp. 147- 156 ,(1991) , 10.5555/114836.114850
Nader H. Bshouty, Paul W. Goldberg, Sally A. Goldman, H. David Mathias, Exact Learning of Discretized Geometric Concepts SIAM Journal on Computing. ,vol. 28, pp. 674- 699 ,(1999) , 10.1137/S0097539794274246
Zhixiang Chen, Wolfgang Maass, On-Line Learning of Rectangles and Unions of Rectangles conference on learning theory. ,vol. 17, pp. 201- 223 ,(1994) , 10.1007/BF00993471
Peter Auer, On-line learning of rectangles in noisy environments conference on learning theory. pp. 253- 261 ,(1993) , 10.1145/168304.168345
Philip M. Long, Lei Tan, PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples Proceedings of the ninth annual conference on Computational learning theory - COLT '96. ,vol. 30, pp. 228- 234 ,(1996) , 10.1145/238061.238105