学会学习的理论模型
Theoretical Models of Learning to Learn
摘要：
机器只有在某种程度上有偏见时才能学习。通常，偏置是手动提供的，例如通过选择一组适当的特征。然而，如果学习机嵌入在相关任务的{ \em环境}中，则它可以通过从环境中学习足够多的任务来{ \em学习}其自身的偏差。本文介绍了偏置学习的两种模型，并给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，而第二个是分层贝叶斯模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
