Mechanisms for Inductive Learning: From Base-learning to Meta-learning

C. Castiello and A.M. Fanelli (Italy)


Inductive Learning, Meta-Learning, Bias Learning, Learning to Learn


This paper briefly surveys the state of the art of a particular mechanism of learning: induction. We discuss inductive mechanisms, drawing attention to the foundation of generalisation success and its lim itations. The distinction between base-learning and meta-learning approaches is pointed out in order to better identify the peculiar attributes of current learn ing strategies. We examine the possibilities to in crease the efficiency of learning algorithms via a meta learning approach, mentioning also some new research lines for further developments on this topic.

Important Links:

Go Back