论文标题
学习学习的理论模型
Theoretical Models of Learning to Learn
论文作者
论文摘要
一台机器只能以某种方式偏见。通常，偏差是手工提供的，例如通过选择合适的功能。但是，如果学习机嵌入了相关任务的{\ em环境}中，则可以通过从环境中学习足够多的任务来学习自己的偏见。在本文中，引入了两种偏见学习模型（或等效地学习学习），并提出了主要的理论结果。第一个模型是基于经验过程理论的PAC型模型，而第二个模型是分层贝叶斯模型。
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.
