Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
Artificial Intelligence
Average case analysis of conjunctive learning algorithms
Proceedings of the seventh international conference (1990) on Machine learning
The general utility problem in machine learning
Proceedings of the seventh international conference (1990) on Machine learning
Proceedings of the sixth international workshop on Machine learning
Embedding decision-analytic control in a learning architecture
Artificial Intelligence - Special issue on knowledge representation
Some studies in machine learning using the game of checkers
Computers & thought
A General Framework for Induction and a Study of Selective Induction
Machine Learning
Shift of bias for inductive concept learning
Shift of bias for inductive concept learning
Building robust learning systems by combining induction and optimization
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Generating production rules from decision trees
IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
The concept of inductive bias can be broken down into the underlying assumptions of the domain, the particular implementation choices that restrict or order the space of hypotheses considered by the learning program (the bias choices), and the inductive policy that links the two. We define inductive policy as the strategy used to make bias choices based on the underlying assumptions. Inductive policy decisions involve addressing trade offs with respect to different bias choices. Without addressing these tradeoffs, bias choices will be made arbitrarily. From the standpoint of inductive policy, we discuss two issues not addressed much in the machine learning literature. First we discuss batch learning with a strict time constraint, and present an initial study with respect to trading off predictive accuracy for speed of learning. Next we discuss the issue of learning in a domain where different types of errors have different associated costs (risks). We show that by using different inductive policies accuracy can be traded off for safety. We also show how the value for the latter tradeoff can be represented explicitly in a system that adjusts bias choices with respect to a particular inductive policy.