Communications of the ACM
Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension
STOC '86 Proceedings of the eighteenth annual ACM symposium on Theory of computing
On the learnability of Boolean formulae
STOC '87 Proceedings of the nineteenth annual ACM symposium on Theory of computing
STOC '87 Proceedings of the nineteenth annual ACM symposium on Theory of computing
Probabilities that imply certainties
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
Concepts that can be expressed as solutions to multilinear pseudo boolean equations with a bounded degree are shown to be learnable in polynomial time from positive examples. This implies the learnability from positive examples of many families of boolean formulae by a unified algorithm. Some of these formulae were not previously known to be learnable, and some were known to be learnable by different algorithms.