Combining Prior Symbolic Knowledge and Constructive Neural Network Learning
作者:
JUSTIN FLETCHER,
ZORAN OBRADOVI[Cgrave],
期刊:
Connection Science
(Taylor Available online 1993)
卷期:
Volume 5,
issue 3-4
页码: 365-375
ISSN:0954-0091
年代: 1993
DOI:10.1080/09540099308915705
出版商: Taylor & Francis Group
关键词: Constructive algorithms;hybrid networks;machine learning.
数据来源: Taylor
摘要:
The concepts of knowledge-based systems and machine learning are combined by integrating an expert system and a constructive neural networks learning algorithm. Two approaches are explored: embedding the expert system directly and converting the expert system rule base into a neural network. This initial system is then extended by constructively learning additional hidden units in a problem-specific manner. Experiments performed indicate that generalization of a combined system surpasses that of each system individually.
点击下载:
PDF (164KB)
返 回