BriefGPT.xyz
Apr, 2019
通过状态空间回归从循环神经网络中提取加权自动机
Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces
HTML
PDF
Takamasa Okudono, Masaki Waga, Taro Sekiyama, Ichiro Hasuo
TL;DR
使用回归方法进行等价查询的加权有限状态自动机（WFA）从循环神经网络（RNN）中提取的新算法实现了最近Weiss、Goldberg和Yahav的DFA提取方法的定量/加权扩展。
Abstract
We present a method to extract a
weighted finite automaton
(WFA) from a
recurrent neural network
(RNN). Our algorithm is based on the WFA learning algorithm by Balle and Mohri, which is in turn an extension of An
→