Theoretical Models of Learning to Learn
Machine Learning
2020-03-02 v1 Machine Learning
Abstract
A Machine can only learn if it is biased in some way. Typically the bias is supplied by hand, for example through the choice of an appropriate set of features. However, if the learning machine is embedded within an {\em environment} of related tasks, then it can {\em learn} its own bias by learning sufficiently many tasks from the environment. In this paper two models of bias learning (or equivalently, learning to learn) are introduced and the main theoretical results presented. The first model is a PAC-type model based on empirical process theory, while the second is a hierarchical Bayes model.
Cite
@article{arxiv.2002.12364,
title = {Theoretical Models of Learning to Learn},
author = {Jonathan Baxter},
journal= {arXiv preprint arXiv:2002.12364},
year = {2020}
}
Comments
arXiv admin note: text overlap with arXiv:1106.0245