发帖
雷达卡
摘要翻译：
机器学习中的一个主要问题是归纳偏差：如何选择学习者的假设空间，使其足够大，以包含正在学习的问题的解决方案，同时又足够小，以确保从合理大小的训练集中可靠地推广。通常，这种偏见是通过专家的技能和洞察力手工提供的。本文研究了一种自动学习偏倚的模型。该模型的核心假设是学习者嵌入到相关学习任务的环境中。在这样的环境中，学习者可以从多个任务中取样，因此，它可以搜索一个假设空间，其中包含对环境中许多问题的良好解决方案。在对学习者可用的所有假设空间集一定的限制下，我们证明了在足够多的训练任务上表现良好的假设空间在同一环境中学习新任务时也会表现良好。明确的界限也被推导出来，证明在一个相关任务的环境中学习多个任务可能比学习一个单一任务更好地概括。
---
英文标题：
《A Model of Inductive Bias Learning》
---
作者：
J. Baxter
---
最新提交年份：
2011
---
分类信息：
一级分类：Computer Science 计算机科学
二级分类：Artificial Intelligence 人工智能
分类描述：Covers all areas of AI except Vision, Robotics, Machine Learning, Multiagent Systems, and Computation and Language (Natural Language Processing), which have separate subject areas. In particular, includes Expert Systems, Theorem Proving (although this may overlap with Logic in Computer Science), Knowledge Representation, Planning, and Uncertainty in AI. Roughly includes material in ACM Subject Classes I.2.0, I.2.1, I.2.3, I.2.4, I.2.8, and I.2.11.
涵盖了人工智能的所有领域，除了视觉、机器人、机器学习、多智能体系统以及计算和语言（自然语言处理），这些领域有独立的学科领域。特别地，包括专家系统，定理证明（尽管这可能与计算机科学中的逻辑重叠），知识表示，规划，和人工智能中的不确定性。大致包括ACM学科类I.2.0、I.2.1、I.2.3、I.2.4、I.2.8和I.2.11中的材料。
--
---
英文摘要：
A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem being learnt, yet small enough to ensure reliable generalization from reasonably-sized training sets. Typically such bias is supplied by hand through the skill and insights of experts. In this paper a model for automatically learning bias is investigated. The central assumption of the model is that the learner is embedded within an environment of related learning tasks. Within such an environment the learner can sample from multiple tasks, and hence it can search for a hypothesis space that contains good solutions to many of the problems in the environment. Under certain restrictions on the set of all hypothesis spaces available to the learner, we show that a hypothesis space that performs well on a sufficiently large number of training tasks will also perform well when learning novel tasks in the same environment. Explicit bounds are also derived demonstrating that learning multiple tasks within an environment of related tasks can potentially give much better generalization than learning a single task.
---
PDF链接：
https://arxiv.org/pdf/1106.0245
京公网安备 11010802022788号
