Contribution Analysis: A Technique for Assigning Responsibilities to Hidden Units in Connectionist Networks
作者:
DENNIS SANGER,
期刊:
Connection Science
(Taylor Available online 1989)
卷期:
Volume 1,
issue 2
页码: 115-138
ISSN:0954-0091
年代: 1989
DOI:10.1080/09540098908915632
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
Contributions, the products of hidden unit activations and weights, are presented as a valuable tool for investigating the inner workings of neural nets. Using a scaled-down version of NETtalk, a fully automated method for summarizing in a compact form both local and distributed hidden-unit responsibilities is demonstrated. Contributions are shown to be more useful for ascertaining hidden-unit responsibilities than either weights or hidden-unit activations. Among the results yielded by contribution analysis: for the example net, redundant output units are handled by identical patterns of hidden units, and the amount of responsibility a hidden unit takes on is inversely proportional to the number of hidden units.
点击下载:
PDF (405KB)
返 回