检索结果-内蒙古大学图书馆

Uniform characterizations of polynomial-query learnabilities

THEORETICAL COMPUTER SCIENCE 2003年第2期292卷 377-385页

作者： Hayashi, Y Matsumoto, S Shinohara, A Takeda, M Kyushu Univ 33 Dept Informat Fukuoka 8128581 Japan Tokai Univ Dept Math Sci Kanagawa 2591292 Japan

We consider the exact learning in the query model. We deal with all types of queries introduced by Angluin: membership, equivalence, superset, subset, disjointness and exhaustiveness queries, and their weak (or restricted) versions where no counterexample is returned. For each of all possible combinations of these queries, we uniformly give complete characterizations of boolean concept classes that are learnable using a polynomial number of polynomial-sized queries. Our characterizations show the equivalence between the learnability of a concept class W using queries and the existence of a good query for any subset H of W which is guaranteed to reject a certain fraction of candidate concepts in H regardless of the answer. As a special case for equivalence queries alone, our characterizations directly correspond to the lack of the approximate fingerprint property, which is known to be a sufficient and necessary condition for the learnability using equivalence queries. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： polynomial-query learning learning from examples concept learning

来源：评论

学校读者我要写书评

暂无评论

Inductive inference of approximations for recursive concepts

引用

THEORETICAL COMPUTER SCIENCE 2005年第1期348卷 15-40页

作者： Lange, S Grieser, G Zeugmann, T Hokkaido Univ Div Comp Sci Sapporo Hokkaido 0600814 Japan Tech Univ Darmstadt FB Informat D-64283 Darmstadt Germany FH Darmstadt FB Informat D-64295 Darmstadt Germany

This paper provides a systematic study of inductive inference of indexable concept classes in learning scenarios where the learner is successful if its final hypothesis describes a finite variant of the target concept, i.e., learning with anomalies. learning from positive data only and from both positive and negative data is distinguished. The following learning models are studied: learning in the limit, finite identification, set-driven learning, conservative inference, and behaviorally correct learning. The attention is focused on the case that the number of allowed anomalies is finite but not a priori bounded. However, results for the special case of learning with an a priori bounded number of anomalies are presented, too. Characterizations of the learning models with anomalies in terms of finite tell-tale sets are provided. The observed varieties in the degree of recursiveness of the relevant tell-tale sets are already sufficient to quantify the differences in the corresponding learning models with anomalies. Finally, a complete picture concerning the relations of all models of learning with and without anomalies mentioned above is derived. (c) 2005 Elsevier B.V. All rights reserved.

关键词： learning theory inductive inference learning with anomalies conservative learning set-driven learning indexed families learning from examples characterization theorems

来源：评论

学校读者我要写书评

暂无评论

DISCRETIZATION ERROR ANALYSIS FOR TIKHONOV REGULARIZATION

引用

ANALYSIS AND APPLICATIONS 2006年第1期4卷 81-99页

作者： De Vito, Ernesto Rosasco, Lorenzo Caponnetto, Andrea Univ Modena Dipartimento Matemat I-41100 Modena Italy Ist Nazl Fis Nucl Sez Genova I-16146 Genoa Italy Univ Genoa DISI I-16146 Genoa Italy MIT CBCL Cambridge MA 02142 USA

We study the discretization of inverse problems defined by a Carleman operator. In particular, we develop a discretization strategy for this class of inverse problems and we give a convergence analysis. learning from ... 详细信息

关键词： learning from examples inverse problems Tikhonov regularization

来源：评论

学校读者我要写书评

暂无评论

Inductive inference of approximations for recursive concepts

Inductive inference of approximations for recursive concepts

引用

11th International Conference on Algorithmic learning Theory (ALT 2000)

关键词： learning theory inductive inference learning with anomalies conservative learning set-driven learning indexed families learning from examples characterization theorems

来源：评论

学校读者我要写书评

暂无评论

A Study of Explanation-Based Methods for Inductive learning

引用

Machine learning 1989年第2期4卷 187-226页

作者： Flann, Nicholas S. Dietterich, Thomas G. Department of Computer Science Oregon State University Corvallis Oregon 97331-3902 United States

This paper formalizes a new learning-from-examples problem: identifying a correct concept definition from positive examples such that the concept is some specialization of a target concept defined by a domain theory. It describes an empirical study that evaluates three methods for solving this problem: explanation-based generalization (EBG), multiple example explanation-based generalization (mEBG), and a new method, induction over explanations (IOE). The study demonstrates that the two existing methods (EBG and mEBG) exhibit two shortcomings: (a) they rarely identify the correct definition, and (b) they are brittle in that their success depends greatly on the choice of encoding of the domain theory rules. The study demonstrates that the new method, IOE, does not exhibit these shortcomings. This method applies the domain theory to construct explanations from multiple training examples as in mEBG, but forms the concept definition by employing a similarity-based generalization policy over the explanations. IOE has the advantage that an explicit domain theory can be exploited to aid the learning process, the dependence on the initial encoding of the domain theory is significantly reduced, and the correct concepts can be learned from few examples. The study evaluates the methods in the context of an implemented system, called Wyl2, which learns a variety of concepts in chess including “skewer” and “knight-fork.” © 1989, Kluwer Academic Publishers. All rights reserved.

关键词： evaluation of learning methods explanation-based learning induction over explanations inductive learning knowledge compilation learning from examples

来源：评论

学校读者我要写书评

暂无评论

ProcessGallery: Contrasting Early and Late Iterations for Design Principle learning

引用

Proceedings of the ACM on Human-Computer Interaction 2024年第CSCW1期8卷 1-35页

作者： Grace Yen, Yu-Chun Jane, L.E. Hyoungwook, J.I.N. Mingyi, L.I. Grace, L.I.N. Pan, Isabelle Yan Dow, Steven P. National Yang Ming Chiao Tung University Hsinchu Taiwan University of California La Jolla San Diego United States KAIST Daejeon South Korea

Traditional design galleries enable users to search for examples based on surface attributes (e.g., color or style), and largely obscure underlying principles (e.g., hierarchy or readability). We conducted three studies to explore how galleries could be constructed to help novices learn key design principles. Study 1 revealed that novices gain perspective by observing how designs evolve throughout a process. Study 2 found that novices are better at identifying design issues when viewing iterations that show improvements for just one principle at a time, rather than multiple. Building on these insights, we created ProcessGallery, a tool that enables users to browse contrasting pairs of early-and-late iterations of designs that highlight key improvements organized by design principles. In Study 3, a within-subjects experiment, sixteen participants iterated on a seed design after viewing examples in ProcessGallery versus a traditional gallery. Using ProcessGallery, participants found more appropriate examples, assessed designs better, and preferred ProcessGallery for learning compared to a traditional gallery. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： design gallery learner-sourcing learning from examples personalized learning vicarious learning Visual design

来源：评论

学校读者我要写书评

暂无评论

A note on evidence and confirmation in machine learning

引用

Computational Intelligence 1989年第3期5卷 180-187页

作者： Delgrande, James P. School of Computing Science Simon Fraser University Burnaby British Columbia V5A 1S6 Canada

This paper addresses the problem in inductive generalization of determining when a general hypothesis is supported by a particular instance. If we accept that, first, some facts do indeed support a general hypothesis and, second, that an instance that supports a hypothesis also supports all logical consequences of the hypothesis, then unintuitive and problematic results are immediately forthcoming. These assumptions lead, for example, to the conclusion that a blue Honda is confirming evidence for the hypothesis that ravens are black. This problem is variously known as the paradoxes of confirmation or Hempel's paradox. In this paper I develop a formal characterization of the problem. The assumption that whatever supports all classical consequences of the hypothesis is rejected. Rather, I argue that a weaker notion of consequence should be adopted for determining what consequences of a hypothesis are supported by the same evidence. An extant formal system for learning from examples is used to address these problems of evidential support, and it is shown that in this framework the problems do not arise. Copyright © 1989, Wiley Blackwell. All rights reserved

关键词： confirmation evidence induction learning from examples ravens.

来源：评论

学校读者我要写书评

暂无评论

Statistical guidance in symbolic learning

引用

Annals of Mathematics and Artificial Intelligence 1990年第1-4期2卷 135-147页

作者： Fisher, Douglas H. Chan, Philip K. Department of Computer Science Vanderbilt University Nashville 37235 TN United States

Concept learning methods of Artificial Intelligence (AI) are usefully guided by statistical measures of concept quality. We review the application of statistical measures in tutored methods of learning from examples, describe the recent application of these measures to conceptual clustering, and propose statistical applications in explanation-based learning. © 1990 J.C. Baltzer A.G. Scientific Publishing Company.

关键词： conceptual clustering explanation-based learning learning from examples Machine learning

来源：评论

学校读者我要写书评

暂无评论

Social networks and web minorities

引用

Cognitive Systems Research 2003年第4期4卷 355-364页

作者： Gori, Marco Numerico, Teresa Dipto. di Ingegneria Informazione Università di Siena 53100 Siena Via Roma 56 Italy Dipto. di Scienze Comunicazione Università di Salerno I-84084 Fisciano Salerno Italy

The conception of appropriate models of information retrieval is a crucial step for the actual growth and development of the web. In addition to traditional information retrieval techniques, nowadays search engines have adopted methods for taking into account the social network deriving from the pattern of interconnections. Using different arguments, it has been shown that this is very effective in practice. In this paper we subscribe that point of view, but state also that social networks based ranking schemes operating on the whole web, like Google's pagerank, prevent small communities to become visible on the Web, regardless of the quality of the information. Hence, we strongly advocate the development of new cognitive models of the whole process of information retrieval which are capable of facing this problem. We give a picture of distributed architectures which incorporates topic-based intelligent agents and personal agents for capturing the user's profile. © 2003 Elsevier B.V. All right reserved.

关键词： Crawling the Web Intelligent agents learning from examples Mining the Web PageRank Web minorities

来源：评论

学校读者我要写书评

暂无评论

Memorable Exemplification in Undergraduate Biology: Instructor Strategies and Student Perceptions

引用

RESEARCH IN SCIENCE EDUCATION 2020年第2期50卷 625-643页

作者： Oliveira, Alandeom W. Bretzlaff, Tiffany Brown, Adam O. SUNY Albany Educ Theory & Practice Dept 1400 Washington AveED 113B Albany NY 12222 USA Univ Ottawa Dept Biol Fac Sci Ottawa ON K1N 6N5 Canada Univ Ottawa Fac Educ Ottawa ON Canada

The present study examines the exemplification practices of a university biology instructor during a semester-long course. Attention is given specifically to how the instructor approaches memorable exemplification-classroom episodes identified by students as a source of memorable learning experiences. A mixed-method research approach is adopted wherein descriptive statistics is combined with qualitative multimodal analysis of video recordings and survey data. Our findings show that memorable experiencing of examples may depend on a multiplicity of factors, including whether students can relate to the example, how unique and extreme the example is, how much detail is provided, whether the example is enacted rather than told, and whether the example makes students feel sad, surprised, shocked, and/or amused. It is argued that, rather than simply assuming that all examples are equally effective, careful consideration needs be given to how exemplification can serve as an important source of memorable science learning experiences.

关键词： Science exemplification learning from examples Undergraduate science Episodic memory

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：