返回
Neural network explanation using inversion
DOI:10.1016/j.neunet.2006.07.005.png)
摘要
En 中文
An important drawback of many artificial neural networks (ANN) is their lack of explanation capability [Andrews, R., Diederich, J., & Tickle, A. B. (1996). A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems, 8, 373-389]. This paper starts with a survey of algorithms which attempt to explain the ANN output. We then present HYPINV,(1) a new explanation algorithm which relies on network inversion; i.e. calculating the ANN input which produces a desired output. HYPINV is a pedagogical algorithm, that extracts rules, in the form of hyperplanes. It is able to generate rules with arbitrarily desired fidelity, maintaining a fidelity-complexity tradeoff. To our knowledge, HYPINV is the only pedagogical rule extraction method, which extracts hyperplane rules from continuous or binary attribute neural networks. Different network inversion techniques, involving gradient descent as well as an evolutionary algorithm, are presented. An information theoretic treatment of rule extraction is presented. HYPINV is applied to example synthetic problems, to a real aerospace problem, and compared with similar algorithms using benchmark problems. (c) 2006 Elsevier Ltd. All rights reserved.
Keyword:
rule extraction
neural network explanation
explanation capability of neural networks
inversion
hyperplanes
evolutionary algorithm
pedagogical
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
7.8K
被引数:
3.0W
机构
暂无机构信息
引用论文
Explanation-based learning and reinforcement learning: A unified view基于解释的学习和强化学习: 一个统一的观点
MACHINE LEARNING
IF2.9
The Role of Lifelong Learning in the Growth of Employment and Labour Efficiency. The Case of Romania

