Communications of the ACM
Logic for problem-solving
Inductive Inference: Theory and Methods
ACM Computing Surveys (CSUR)
Human Problem Solving
Journal of Computer and System Sciences
What do Constructive Learners Really Learn?
Artificial Intelligence Review
A Simulated Annealing-Based Learning Algorithm for Boolean DNF
AI '99 Proceedings of the 12th Australian Joint Conference on Artificial Intelligence: Advanced Topics in Artificial Intelligence
Generalized Graph Colorability and Compressibility of Boolean Formulae
ISAAC '98 Proceedings of the 9th International Symposium on Algorithms and Computation
Learning Range Restricted Horn Expressions
EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
ALT '99 Proceedings of the 10th International Conference on Algorithmic Learning Theory
Smooth Boosting and Learning with Malicious Noise
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
When Can Two Unsupervised Learners Achieve PAC Separation?
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Agnostically Learning Halfspaces
FOCS '05 Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science
Using coverage as a model building constraint in learning classifier systems
Evolutionary Computation
Learning one-counter languages in polynomial time
SFCS '87 Proceedings of the 28th Annual Symposium on Foundations of Computer Science
Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
SFCS '87 Proceedings of the 28th Annual Symposium on Foundations of Computer Science
Learning Halfspaces with Malicious Noise
ICALP '09 Proceedings of the 36th International Colloquium on Automata, Languages and Programming: Part I
Learning Halfspaces with Malicious Noise
The Journal of Machine Learning Research
Learning conjunctive concepts in structural domains
AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Learning conjunctive concepts in structural domains
AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Probably approximately correct learning
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Analyses of instance-based learning algorithms
AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2
Algorithms and theory of computation handbook
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Sensitive error correcting output codes
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Proceedings of the 15th International Conference on Database Theory
An approach to guided learning of boolean functions
Mathematical and Computer Modelling: An International Journal
A Computational Learning Theory of Active Object Recognition Under Uncertainty
International Journal of Computer Vision
ACM Transactions on Database Systems (TODS) - Invited papers issue
Hi-index | 0.00 |
The question of whether concepts expressible as disjunctions of conjunctions can be learned from examples in polynomial time is investigated. Positive results are shown for significant subclasses that allow not only propositional predicates but also some relations. The algorithms are extended so as to be provably tolerant to a certain quantifiable error rate in the examples data. It is further shown that under certain restrictions on these subclasses the learning algorithms are well suited to implementation on neural networks of threshold elements. The possible importance of disjunctions of conjunctions as a knowledge representation stems from the observations that on the one hand humans appear to like using it andon the other, that there is circumstantial evidence that significantly larger classes may not be learnable in polynomial time. An NP-completeness result corroborating the latter is also presented.