资源论文Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

2020-03-11 | |  62 |   44 |   0

Abstract

We present a novel algorithm that uses exact learning and abstraction to extract a deterministic finite automaton describing the state dynamics of a given trained RNN. We do this using Angluin’s L* algorithm as a learner and the trained RNN as an oracle. Our technique efficiently extracts accurate automata from trained RNNs, even when the state vectors are large and require fine differentiation.

上一篇:First Order Generative Adversarial Networks

下一篇:PixelSNAIL: An Improved Autoregressive Generative Model

用户评价
全部评价

热门资源

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • dynamical system ...

    allows to preform manipulations of heavy or bul...

  • The Variational S...

    Unlike traditional images which do not offer in...