An Approach to Combining Explanation-based and Neural Learning Algorithms
作者:
JUDEW. SHAVLIK,
GEOFFREYG. TOWELL,
期刊:
Connection Science
(Taylor Available online 1989)
卷期:
Volume 1,
issue 3
页码: 231-253
ISSN:0954-0091
年代: 1989
DOI:10.1080/09540098908915640
出版商: Taylor & Francis Group
关键词: Explanation-based learning;neural networks;connectionism;symbolic systems;imperfect domain theories;neural network topologies;hybrid machine learning systems
数据来源: Taylor
摘要:
Machine learning is an area where both symbolic and neural approaches to artificial intelligence have been heavily investigated. However, there has been little research into the synergies achievable by combining these two learning paradigms. A hybrid system that combines the symbolically-oriented explanation-based learning paradigm with the neural backpropagation algorithm is described. In the presented EBL-ANN algorithm, the initial neural network configuration is determined by the generalized explanation of the solution to a specific classification task. This approach overcomes problems that arise when using imperfect theories to build explanations and addresses the problem of choosing a good initial neural network configuration. Empirical results show that the hybrid system more accurately learns a concept than the explanation-based system by itself and learns faster and generalizes better than the neural learning system by itself.
点击下载:
PDF (424KB)
返 回