Learning with Inscrutable Theories

机译：难以理解的理论学习

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper addresses the problem of learning problem solving knowledge when the domain theory of the learning system is inscrutable, i.e., not represented declaratively. We draw the following conclusions: First, although most of the algorithms and methods investigated in Explanation-Based Learning (EBL) literature assume declarative theories, at least in some domains, similar speedups can be achieved by simpler techniques that do not make this assumption. Second, learning with inscrutable theories blurs the distinction between "empirical" and "explanation-based" methods, both of which can be viewed as implementing some form of bias in their algorithms. Third, the utility problem is best addressed by implementing a bias that exploits the structure of the domain. We support our conclusions with experiments in the Eight Puzzle domain.

机译：本文讨论了在学习系统的领域理论难以理解（即不以声明方式表示）时学习解决问题的知识的问题。我们得出以下结论：首先，尽管基于解释学习（EBL）文献中研究的大多数算法和方法都采用了声明性理论，至少在某些领域中，可以通过不采用此假设的简单技术来实现类似的加速。其次，难以理解的理论学习模糊了“经验”和“基于解释”方法之间的区别，这两种方法都可以视为在其算法中实现了某种形式的偏差。第三，通过实施利用领域结构的偏差可以最好地解决效用问题。我们通过在“八拼图”领域进行的实验来支持我们的结论。

著录项

来源
《Machinee learning》|1991年|544-548|共5页
会议地点 Evanston IL(US);Evanston IL(US)
作者
Prasad Tadepalli;
展开▼
作者单位

Department of Computer Science Oregon State University Corvallis, OR 97331-3202;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类计算机的应用;
关键词

相似文献

外文文献
中文文献
专利

1. Associative Learning as Higher Order Cognition: Learning in Human and Nonhuman Animals From the Perspective of Propositional Theories and Relational Frame Theory [J] . De Houwer Jan, Hughes Sean, Barnes-Holmes Dermot Journal of comparative psychology . 2016,第3期

机译：作为高阶认知的联想学习：命题理论和关系框架理论视角下的人类和非人类动物学习
2. The (kinetic) theory of active particles applied to learning dynamics Comment on "Collective learning modeling based on the kinetic theory of active particles" by D. Burini et al. [J] . Nieto J. Physics of life reviews . 2016,第Null期

机译：活性粒子的（动力学）理论应用于学习动力学评论D. Burini等人的“基于活性粒子动力学理论的集体学习建模”。
3. Learning From Learning Theory: A Model of Organizational Adoption Strategies at the Microfoundations of Institutional Theory [J] . Chandler David, Hwang Hokyu Journal of Management . 2015,第5期

机译：从学习理论中学习：制度理论微观基础上的组织采用策略模型
4. Inscrutable Decision Makers: Knightian Uncertainty in Machine Learning [C] . Rick Hangartner, Paul Cull International conference on computer aided systems theory . 2018

机译：神秘的决策者：机器学习中的骑士不确定性
5. The Inscrutable Spirit of Louis Sullivan: Transcendentalism and American Architecture at the Turn of the Twentieth Century [D] . Ellis, Isaiah. 2018

机译：路易·沙利文不可思议的精神：20世纪初的先验主义与美国建筑
6. The Efficacy of Three Learning Methods Collaborative Context-Based Learning and Traditional on Learning Attitude and Behaviour of Undergraduate Nursing Students: Integrating Theory and Practice [O] . Ali Hasanpour-Dehkordi, Kamal Solati 2016

机译：三种学习方法的协作基于上下文的学习和传统的学习对本科护理学生学习态度和行为的功效：理论与实践的结合
7. Imitating Inscrutable Enemies: Learning from Stochastic Policy Observation, Retrieval and Reuse [O] . Kellen Gillespie, Justin Karneeb, Stephen Lee-urban, 2010

机译：模仿不可思议的敌人：学习随机政策观察，检索和重用

Learning with Inscrutable Theories

摘要

著录项

相似文献

相关主题

期刊订阅