Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
Artificial Intelligence
COLT '90 Proceedings of the third annual workshop on Computational learning theory
Learning hierarchical rule sets
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Learning Boolean Functions in an Infinite Attribute Space
Machine Learning
An introduction to computational learning theory
An introduction to computational learning theory
Learning in the presence of finitely or infinitely many irrelevant attributes
Journal of Computer and System Sciences
On learning decision trees with large output domains (extended abstract)
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
On learning width two branching programs (extended abstract)
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Attribute-efficient learning in query and mistake-bound models
Journal of Computer and System Sciences
STOC '99 Proceedings of the thirty-first annual ACM symposium on Theory of computing
Machine Learning
A Neuroidal Architecture for Cognitive Computation
ICALP '98 Proceedings of the 25th International Colloquium on Automata, Languages and Programming
Human Problem Solving
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
A neuroidal architecture for cognitive computation
Journal of the ACM (JACM)
Evidence that Incremental Delta-Bar-Delta Is an Attribute-Efficient Linear Learner
ECML '02 Proceedings of the 13th European Conference on Machine Learning
Experiments with Projection Learning
DS '02 Proceedings of the 5th International Conference on Discovery Science
On online learning of decision lists
The Journal of Machine Learning Research
Theory revision with queries: horn, read-once, and parity formulas
Artificial Intelligence
Toward Attribute Efficient Learning of Decision Lists and Parities
The Journal of Machine Learning Research
Theoretical Computer Science
Projective DNF formulae and their revision
Discrete Applied Mathematics
Online closure-based learning of relational theories
ILP'05 Proceedings of the 15th international conference on Inductive Logic Programming
| Hi-index | 0.00 |
A method of combining learning algorithms is described that preserves attribute-efficiency. It yields learning algorithms that require a number ofexamples that is polynomial in the number of relevant variables andlogarithmic in the number of irrelevant ones. The algorithms aresimple to implement and realizable on networks with a number of nodeslinear in the total number of variables. They includegeneralizations of Littlestone‘s Winnow algorithm, and are,therefore, good candidates for experimentation on domains having verylarge numbers of attributes but where nonlinear hypotheses aresought.