检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

67 篇 会议
1 篇 期刊文献

馆藏范围

68 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

58 篇 工学
- 54 篇 计算机科学与技术...
- 44 篇 软件工程
- 11 篇 信息与通信工程
- 9 篇 光学工程
- 9 篇 材料科学与工程（可...
- 9 篇 控制科学与工程
- 7 篇 生物工程
- 5 篇 生物医学工程（可授...
- 2 篇 机械工程
- 2 篇 仪器科学与技术
- 2 篇 电子科学与技术（可...
- 2 篇 建筑学
- 2 篇 土木工程
- 1 篇 力学（可授工学、理...
- 1 篇 电气工程
- 1 篇 轻工技术与工程
- 1 篇 安全科学与工程
29 篇 理学
- 18 篇 数学
- 10 篇 物理学
- 7 篇 生物学
- 7 篇 统计学（可授理学、...
- 2 篇 系统科学
8 篇 管理学
- 5 篇 图书情报与档案管...
- 2 篇 管理科学与工程(可...
- 2 篇 工商管理
3 篇 法学
- 3 篇 社会学
2 篇 医学
- 2 篇 临床医学
- 1 篇 基础医学(可授医学...
- 1 篇 药学(可授医学、理...
1 篇 军事学

主题

4 篇 learning systems
4 篇 object recogniti...
3 篇 trees (mathemati...
2 篇 reinforcement le...
2 篇 artificial intel...
2 篇 computer vision
2 篇 computer games
1 篇 structural optim...
1 篇 wheelchairs
1 篇 genetic programm...
1 篇 knowledge based ...
1 篇 message passing
1 篇 motion planning
1 篇 probability dist...
1 篇 reflection
1 篇 visibility
1 篇 cameras
1 篇 brain
1 篇 learning algorit...
1 篇 search engines

机构

2 篇 computer science...
2 篇 center for artif...
2 篇 department of co...
2 篇 computer science...
1 篇 boston universit...
1 篇 school of comput...
1 篇 department of co...
1 篇 lifia- imag- inr...
1 篇 computer science...
1 篇 computer vision ...
1 篇 department of co...
1 篇 volen center for...
1 篇 department of co...
1 篇 vrije universite...
1 篇 department of co...
1 篇 school of comput...
1 篇 department of co...
1 篇 computer science...
1 篇 computer science...
1 篇 dept. of electri...

作者

2 篇 markovitch shaul
2 篇 smith stephen j....
2 篇 lowe david g.
2 篇 draper bruce a.
2 篇 mutchler david
2 篇 nau dana s.
2 篇 zemel richard s.
1 篇 marpaung andreas...
1 篇 korf richard e.
1 篇 hille david
1 篇 chachere lawrenc...
1 篇 tecuci gheorghe
1 篇 segen jakub
1 篇 pierce david
1 篇 johnson m.
1 篇 hinton geoffrey ...
1 篇 beis jeffrey s.
1 篇 roberts jennifer
1 篇 hieb michael r.
1 篇 murase hiroshi

语言

68 篇 英文

检索条件"任意字段=1993 AAAI Fall Symposium on Learning in Computer Vision"

共 68 条记录，以下是51-60 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

learning combination of evidence functions in object recognition

Learning combination of evidence functions in object recogni...

引用

1993 aaai fall symposium on learning in computer vision

作者： Cook, Diane J. Woods, Kevin Hall, Lawrence O. Stark, Louise Bowyer, Kevin Department of Computer Science and Engineering University of South Florida TampaFL33620 United States Dept.of CS Univ.of thePacific StocktonCA United States

This paper describes a learning system, OMLET, which helps to automate the construction of function-based object recognition systems. OMLET is designed to learn fuzzy membershipfunctions which approximate the allowable ranges of physical dimensions such as width, area, relative orientation, etc. The learning is done by iterative error reduction on a set of labeled training examples. Results from a chair domain show that the system is capable of learning the fuzzy membership functions. © 1993 AI Access Foundation. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

learning VISUAL SPEECH

LEARNING VISUAL SPEECH

引用

1993 aaai fall symposium on learning in computer vision

作者： Wolff, Gregory J. Venkatesh Prasad, K. Stork, David G. Hennecke, Marcus Machine Learning and Perception Group Ricoh California Research Center 2882 Sand Hill Road Suite 115 Menlo ParkCA94025-7022 United States Dept. of Electrical Engineering MC4055 Stanford University StanfordCA1305 United States

The performance of Automatic Speech Recognition (ASR) systems can be greatly enhanced by incorporating phonologically relevant features contained in video sequences of speakers. Humans, particularly the hearing impaired, can utilize visual information- through lipreading - for improvedaccuracy. Wepresent a system for doing ASRthat relies on both classical and learning algorithms to identify and process relevant visual information. Classical image processing operations such as convolution and thresholding are used to reduce each frame to a small intermediate (vector) representation of the image content. Sequences of these vectors are used as inputs to a modified time delay neural network, which is trained to output the corresponding phoneme. The network learns to extract visual-temporal features which are usefill in classification. Eventually, the learning procedure may be extented to directly utilize the "raw" pixels, however, in present practice, the classical operations act as a means of compressing the visual informatiou down to manageable amounts. Our current visual speech recognizer, in combination with a similar acoustic recognizer reduces the error rate by 75 % when compared with the acoustic subsystem alone. © 1993 AI Access Foundation. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A COMPARISON BETWEEN PROBABILISTIC SEARCH AND WEIGHTED HEURISTICS IN A GAME WITH INCOMPLETE INFORMATION

A COMPARISON BETWEEN PROBABILISTIC SEARCH AND WEIGHTED HEURI...

引用

1993 aaai fall symposium on Games: Planning and learning

作者： Gordon, Steven Department of Mathematics East Carolina University GreenvilleNC27858 United States

Computing an effective strategy in games with incomplete information is much more difficult than in games where the status of every relevant factor is known. A weighted heuristic approach selects the move in a given position that maximizes a weighted sum of known factors, where the weights have been optimized over a large random sample of games. Probabilistic search is an alternative approach that generates a random set of scenarios, simulates how plausible moves perform under each scenario, and selects the move with the "best"overall performance. This paper compares the effectiveness of these approaches for the game of Scrabble. © 1993, aaai (***). All rights reserved.

关键词： computer games

来源：评论

学校读者我要写书评

暂无评论

learning Models of Opponent's Strategy in Game Playing

Learning Models of Opponent's Strategy in Game Playing

引用

1993 aaai fall symposium on Games: Planning and learning

作者： Carmel, David Markovitch, Shaul Computer Science Department Technion Haifa32000 Israel

Most of the activity in the area of game playing programs is concerned with efficient ways of searching game trees. There is substantial evidence that game playing involves additional types of intelligent processes. One such process performed by human experts is the acquisition and usage of a model of their opponent's strategy. This work studies the problem of opponent modelling in game playing. A simplified version of a model is defined as a pair of search depth and evaluation function. M∗ a generalization of the minimax algorithm that can handle an opponent model, is described. The benefit of using opponent models is demonstrated by comparing the performance of M∗ with that of the traditional minimax algorithm. An algorithm for learning the opponent's strategy using its moves as examples was developed. Experiments demonstrated its ability to acquire very accurate models. Finally, a full model-learning game-playing system was developed and experimentally demonstrated to have advantage over non-learning player. © 1993, aaai (***). All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

THE PRAX APPROACH TO learning A LARGE NUMBER OF TEXTURE CONCEPTS

THE PRAX APPROACH TO LEARNING A LARGE NUMBER OF TEXTURE CONC...

引用

1993 aaai fall symposium on learning in computer vision

作者： Bala, J. Michalski, R. Wnek, J. Center for Artificial Intelligence George Mason University FairfaxVA22030 United States

This paper describes an approach, called PRAX, to learning descriptions of a large number of texture concepts from texture samples. The learning process consists of two phases: 1) learning descriptions of selected subset of texture classes, called principal axes (briefly, praxes), and 2) learning descriptions of other classes (non-praxclasses), by relating themto the praxes. Descriptions of non-prax classes are expressed in terms of the similarities to praxes, and thus the second phase represents a form of analogical learning. Whilethe first phase is doneas a one-step learning process, the second phase is performed as an incremental learning process. The method was applied to learning texture concepts from texture samples, and illustrated by an experiment on learning 24 texture classes, using a subset of 8 classes to learn praxes. After acquiring all texture descriptions from samples taken from a training area, the implemented program, PRAX-2, recognized texture samples from the testing area withouta single error. © 1993 AI Access Foundation. All rights reserved.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Physics of State-Space Search

Exploiting the Physics of State-Space Search

引用

1993 aaai fall symposium on Games: Planning and learning

作者： Levinson, Robert Dept. of Computer and Information Sciences University of California Santa CruzCA95060 United States

This paper is a blueprint for the development of a fully domain-independent single agent and multi-agent heuristic search system. The paper gives a graph-theoretic representation of search problems based on conceptual graphs, and outlines two different learning systems. One, an "informed learner"makes use of the the graph-theoretic definition of a search problem or game in playing and adapting to a game in the given environment. The other a "blind learner"is not given access to the rules of a domain, but must discover and then exploit the underlying mathematical structure of a given domain. These learning agents are based on generalizing the understanding obtained with the Morph chess system to all games involving the interactions of abstract mathematical relations. Blind learner can be viewed as a type of neural network that makes explicit use of fuzzy graph-isomorphism to exploit at a "meta-level"analogous states of the net itself. Publically available software has been developed for supporting research in blind learning and informed learning in the context of general problem-solving. The paper is based on studying the graph-theoretic structure of large open problems in machine learning research and giving a reasoned, unifying, framework for working toward their solution. In a field seeking comprehensive theories and general testbeds we hope that providing such a framework and software for exploration is an important contribution. The ultimate success of the framework awaits further investigation. © 1993, aaai (***). All rights reserved.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Developing Population Codes For Object Instantiation Parameters

Developing Population Codes For Object Instantiation Paramet...

引用

1993 aaai fall symposium on learning in computer vision

作者： Zemel, Richard S. Hinton, Geoffrey E. University of Toronto & The Salk Institute CNL 10010 North Torrey Pines Rd. La Jolla San DiegoCA92037 United States Computer Science Department University of Toronto 6 King’s College Rd TorontoONM5S 1A4 Canada

An efficient and useful representation for an object viewed from different positions is in terms of its instantiation parameters. Weshow how the MinimumDescription Length principle (MDL)can be used to train the hidden units of a neural network to develop a population code for the instantiation parameters of an object in an image. Each hidden unit has a location in a low-dimensionalimplicit space. If the hidden unit activities form a standard shape (a bump) in this space, they can be cheaply encoded by the center of this bump. So the weights from the input units to the hidden units in a self-supervised network are trained to make the activities form a bump. The coordinates of the hidden units in the implicit space are also learned, thus allowing flexibility, as the network develops separate population codes when presented with different objects. © 1993 AI Access Foundation. All rights reserved.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

Designing A computer Opponent for Wargames: Integrating Planning, Knowledge Acquisition and learning in WARGLES

Designing A Computer Opponent for Wargames: Integrating Plan...

引用

1993 aaai fall symposium on Games: Planning and learning

作者： Hieb, Michael R. Hille, David Tecuci, Gheorghe Center for Artificial Intelligence Department of Computer Science George Mason University 4400 University Drive FairfaxVA22030-4444 United States ANSER ArlingtonVA22202 United States Romanian Academy Bucharest Romania

This paper presents a general approach to designing a computer opponent for nondeterministic adversarial games which is able to learn from interaction with a human expert. This approach is based on an integration of planning, knowledge acquisition and learning. We illustrate this approach with WARGLES (WARGame learning System), which plays strategic level wargames. WARGLES consists of a game playing system, a computer opponent and a learning component for the computer opponent. The computer opponent utilizes an adversarial planner with an incomplete and partially incorrect knowledge base. The learning component revises this knowledge base to improve the quality of play of the computer opponent based on interactions with an expert. © 1993, aaai (***). All rights reserved.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

A Strategic Metagame Player for General Chess-Like Games

A Strategic Metagame Player for General Chess-Like Games

引用

1993 aaai fall symposium on Games: Planning and learning

作者： Pell, Barney Computer Laboratory University of Cambridge CambridgeCB2 3QG United Kingdom

This paper reviews the concept of Metagame and discusses the implementation of metagamer, a program which plays Metagame in the class of symmetric chess-like games, which includes chess, Chinese-chess, checkers, draughts, and Shogi. The program takes as input the rules of a specific game and analyses those rules to construct for that game an efficient representation and an evaluation function, both for use with a generic search engine. The strategic analysis performed by the program relates a set of general knowledge sources to the details of the particular game. Among other properties, this analysis determines the relative value of the different pieces in a given game. Although metagamer does not learn from experience, the values resulting from its analysis are qualitatively similar to values used by experts on known games, and are sufficient to produce competitive performance the first time the program actually plays each game it is given. This appears to be the first program to have derived useful piece values directly from analysis of the rules of different games. © 1993, aaai (***). All rights reserved.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Collaborative Applications for Long-Term Use

Collaborative Applications for Long-Term Use

引用

1993 aaai fall symposium on Human-computer Collaboration

作者： Eisenberg, Michael Department of Computer Science Institute of Cognitive Science University of Colorado Boulder BoulderCO80309-0430 United States

computer applications are designed, used, and assessed by (often unstated) analogy to other tools and devices. When viewed as appliances (e.g., telephones), applications are created and judged according to standards of ease of use and rapid learnability;when viewed, by contrast, as creative media (e.g., musical instruments), standards of expressiveness and flexibility become more salient. In designing this second type of application, providing the user with long-term creative power often necessitates an acceptance of various forms of complexity within the application-for example, the application may include a "task-enriched" programming environment;and further, making such an application truly collaborative suggests the inclusion of features and tools that will support users in learning both the application itself (including the programming language) and the domain of the application. This paper elaborates on these observations, discussing the design of collaborative applications for creative, long-term use (and contrasting this design strategy with the dominant current trend in application development). The paper concludes with a brief description of our own efforts in collaborative application design: namely, the programmable design environments currently being prototyped in our laboratory. copyright © 1993, aaai (***). All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共7页 << < 1 2 3 4 5 6 7 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：