Machine Learning - Special issue on inductive transfer
Knowledge Incorporation into Neural Networks From Fuzzy Rules
Neural Processing Letters
On the Need for a Neural Abstract Machine
Sequence Learning - Paradigms, Algorithms, and Applications
Learning with side information: PAC learning bounds
Journal of Computer and System Sciences
Training without data: knowledge insertion into RBF neural networks
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Multi-dimensional data construction method with its application to learning from small-sample-sets
Intelligent Data Analysis
Towards user-centric memetic algorithms: experiences with the TSP
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
Artificial Intelligence in Medicine
Hi-index | 0.00 |
Learning from hints is a generalization of learning fromexamples that allows for a variety of information about the unknownfunction to be used in the learning process. In this paper, we usethe VC dimension, an established tool for analyzing learning fromexamples, to analyze learning from hints. In particular, we showhow the VC dimension is affected by the introduction of a hint. Wealso derive a new quantity that defines a VC dimension for the hintitself. This quantity is used to estimate the number of examplesneeded to "absorb" the hint. We carry out the analysis for twotypes of hints, invariances and catalysts. We also describe how thesame method can be applied to other types of hints.