Towards interpreting recurrent neural networks through probabilistic abstraction-Reference-Cited by-同舟云学术

Towards interpreting recurrent neural networks through probabilistic abstraction

Published:2020-12-21 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering
language:
Short-container-title:

Author:

Dong Guoliang¹,Wang Jingyi¹,Sun Jun²,Zhang Yang¹,Wang Xinyu¹,Dai Ting³,Dong Jin Song⁴,Wang Xingen¹

Affiliation:

1. Zhejiang University

2. Singapore Management University

3. Huawei International Pte Ltd

4. National University of Singapore

Funder

Project of Science and Technology Research and Development Program of China Railway Corporation

Key-Area Research and Development Program of Guangdong Province

Fundamental Research Funds for the Zhejiang University NGICS Platform

National Research Foundation, Prime Minister?s Office, Singapore under its Corporate Laboratory@University Scheme, National University of Singapore, and Singapore Telecommunications Ltd

National Key R&D Program of China

National Research Foundation, Singapore under its AI Singapore Programme

NSFC Program

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3324884.3416592

Reference51 articles.

1. https://pytorch.org/. https://pytorch.org/.

2. https://github.com/dgl-prc/rnn2automata. https://github.com/dgl-prc/rnn2automata.

3. Learning regular sets from queries and counterexamples

Cited by 12 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. LUNA: A Model-Based Universal Analysis Framework for Large Language Models;IEEE Transactions on Software Engineering;2024-07

2. Particle Swarm Optimization-Based Model Abstraction and Explanation Generation for a Recurrent Neural Network;Algorithms;2024-05-13

3. Learning minimal automata with recurrent neural networks;Software and Systems Modeling;2024-03-21

4. Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data;Proceedings of the IEEE/ACM 46th International Conference on Software Engineering;2024-02-06

5. Differential Safety Testing of Deep RL Agents Enabled by Automata Learning;Bridging the Gap Between AI and Reality;2023-12-14