Interpretation of neural networks as Boolean transfer functions
作者：
Highlights：
•
摘要
An algorithm for converting neural networks into Boolean functions is presented. The absence of such an algorithm has been identified in the literature as a significant problem, and the solution shown in the paper is both complete and efficient. The analysis of the algorithm shows it to have a time complexity of better than 2N−1 − 2(N2)−1 + 1.
论文关键词：neural networks,rule extraction,rule induction
论文评审过程：Received 4 March 1993, Revised 28 May 1993, Accepted 19 July 1993, Available online 19 February 2003.
论文官网地址：https://doi.org/10.1016/0950-7051(94)90007-8
