QAMLセミナー
日時：2019年11月27日(水) 16:45-18:00
場所：NII, 12F 1208
タイトル: Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces
発表者：関山太郎, 助教, NII
概要：
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 Angluin's classic \lstar algorithm. Our technical novelty is in the use of regression methods for the so-called equivalence queries, thus exploiting the internal state space of an RNN. This way we achieve a quantitative extension of the recent work by Weiss, Goldberg and Yahav that extracts DFAs. Experiments demonstrate that our algorithm's practicality.
参加をご希望の方は、吉岡までお知らせください。