检索结果-内蒙古大学图书馆

Dynamically adding symbolically meaningful nodes to knowledge-based neural networks

KNOWLEDGE-BASED SYSTEMS 1995年第6期8卷 301-311页

作者： Opitz, DW Shavlik, JW Computer Sciences Department University of Wisconsin 1210 West Dayton Street Madison WI 53706 USA

Traditional connectionist theory-refinement systems map the dependencies of a domain-specific rule base into a neural network, and then refine this network using neural learning techniques. Most of these systems, however, lack the ability to refine their network's topology and are thus unable to add new rules to the (reformulated) rule base. Therefore, with domain theories that lack rules, generalization is poor, and training can corrupt the original rules - even those that were initially correct. The paper presents TopGen, an extension to the kbann algorithm, which heuristically searches for possible expansions to the kbann network. TopGen does this by dynamically adding hidden nodes to the neural representation of the domain theory, in a manner that is analogous to the adding of rules and conjuncts to the symbolic rule base. Experiments indicate that the method is able to heuristically find effective places to add nodes to the knowledge bases of four real-world problems, as well as an artificial chess domain. The experiments also verify that new nodes must be added in an intelligent manner. The algorithm showed statistically significant improvements over the kbann algorithm in all five domains.

关键词： network-growing algorithms theory refinement kbann algorithm computational biology

来源：评论

学校读者我要写书评

暂无评论

The Idea of Knowledge Supplementation and Explanation Using Neural Networks to Support Decisions in Construction Engineering

引用

Procedia Engineering 2013年 57卷 302-309页

作者： Marcin Gajzler Institute of Structural Engineering Faculty of Civil and Environmental Engineering Poznan University of Technology Piotrowo 5 PL-60-965 Poznan Poland

The article presents the problem of knowledge in knowledge-based systems, such as advisory systems used in construction engineering. The unique characteristics of construction engineering translate directly into unique characteristics of knowledge resources, which is evident in the potential sources of knowledge. Many of them are not open, uncertain, fuzzy, of different credibility, and incomplete. One of the knowledge sources is the mental models of experts working in specific fields of construction engineering. Based on the knowledge acquisition sessions that have been completed, it can be concluded that only a certain part of the knowledge contained in mental models has been acquired. In order to ensure more completeness of the knowledge and explain the mechanism of inference, the kbann (Knowledge Based Artificial Neural Network) algorithm was used, which enables extracting rules that are not a part of the original state of knowledge using trained neural networks. This method effectively supports the process of construction of advisory systems.

关键词： Knowledge acquisition kbann algorithm Decision systems

来源：评论

学校读者我要写书评

暂无评论

Actively Searching for an Effective Neural Network Ensemble

引用

Connection Science 1996年第3-4期8卷 337-337页

作者： Opitz, D. W. Shavlik, J. W. Computer Science Department University of Minnesota 320 Heller Hall Duluth MN 55812 10 University Drive United States Computer Sciences Department University of Wisconsin Madison WI 53706 1210 W. Dayton Street United States Department of Computer Science University of Montana Missoula MT 59812 United States

A neural network (NN) ensemble is a very successful technique where the outputs of a set of separately trained NNs are combined to form one unified prediction. An effective ensemble should consist of a set of networks that are not only highly correct, but ones that make their errors on different parts of the input space as well;however, most existing techniques only indirectly address the problem of creating such a set. We present an algorithm called ADDEMUP that uses genetic algorithms to search explicitly for a highly diverse set of accurate trained networks. ADDEMUP works by first creating an initial population, then uses genetic operators to create new networks continually, keeping the set of networks that are highly accurate while disagreeing with each other as much as possible. Experiments on four real-world domains show that ADDEMUP is able to generate a set of trained networks that is more accurate than several existing ensemble approaches. Experiments also show ADDEMUP is able to incorporate prior knowledge effectively, if available, to improve the quality of its ensemble.

关键词： Bagging algorithm Genetic algorithms kbann algorithm Knowledge-based neural networks REGENT algorithm

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：