Communications of the ACM
Computational limitations on learning from examples
Journal of the ACM (JACM)
A general lower bound on the number of examples needed for learning
Information and Computation
Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
A Learning Criterion for Stochastic Rules
Machine Learning - Computational learning theory
Efficient noise-tolerant learning from statistical queries
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Efficient distribution-free learning of probabilistic concepts
Journal of Computer and System Sciences - Special issue: 31st IEEE conference on foundations of computer science, Oct. 22–24, 1990
Composite geometric concepts and polynomial predictability
Information and Computation
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Solving the multiple instance problem with axis-parallel rectangles
Artificial Intelligence
Approximating hyper-rectangles: learning and pseudo-random sets
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
A Note on Learning from Multiple-Instance Examples
Machine Learning - Special issue on the ninth annual conference on computational theory (COLT '96)
Real-Valued Multiple-Instance Learning with Queries
ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
Multiple-Instance Learning of Real-Valued Geometric Patterns
Annals of Mathematics and Artificial Intelligence
Multiple instance learning of real valued data
The Journal of Machine Learning Research
Improve Multi-Instance Neural Networks through Feature Selection
Neural Processing Letters
Multi-Instance Learning Based Web Mining
Applied Intelligence
Adapting RBF Neural Networks to Multi-Instance Learning
Neural Processing Letters
MILES: Multiple-Instance Learning via Embedded Instance Selection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Solving multi-instance problems with classifier ensemble based on constructive clustering
Knowledge and Information Systems - Special Issue on Mining Low-Quality Data
Fuzzy lattice reasoning (FLR) classifier and its application for ambient ozone estimation
International Journal of Approximate Reasoning
A Multiple Instance Learning Strategy for Combating Good Word Attacks on Spam Filters
The Journal of Machine Learning Research
A Multi-Instance Learning Algorithm Based on Normalized Radial Basis Function Network
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Multi-instance genetic programming for web index recommendation
Expert Systems with Applications: An International Journal
Multi-instance clustering with applications to multi-instance prediction
Applied Intelligence
Real-valued multiple-instance learning with queries
Journal of Computer and System Sciences
Multiple instance learning with genetic programming for web mining
IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
G3P-MI: A genetic programming algorithm for multiple instance learning
Information Sciences: an International Journal
Multi-instance multi-label learning
Artificial Intelligence
Multi-instance learning with any hypothesis class
The Journal of Machine Learning Research
Hi-index | 0.00 |
We describe a polynomial-time algorithm for learning axis-alignedrectangles in Q^d with respect to product distributionsfrom multiple-instance examples in the PAC model. Here, each exampleconsists of n elements of Q^d together witha label indicating whether any of the n points is in therectangle to be learned. We assume that there is an unknown productdistribution D over Q^d such that allinstances are independently drawn according to D. The accuracyof a hypothesis is measured by the probability that it would incorrectlypredict whether one of n more points drawn from Dwas in the rectangle to be learned. Our algorithm achieves accuracy εwith probability 1-δ in O\left(\frac{d^5n^{12}}{\epsilon^{20}} \log^2 \frac{nd}{\epsilon\delta}\right) time.