2019 AAAI AAAI 2019

Verification of RNN-Based Neural Agent-Environment Systems

Abstract

Abstract We introduce agent-environment systems where the agent is stateful and executing a ReLU recurrent neural network. We define and study their verification problem by providing equivalences of recurrent and feed-forward neural networks on bounded execution traces. We give a sound and complete procedure for their verification against properties specified in a simplified version of LTL on bounded executions. We present an implementation and discuss the experimental results obtained.

🚀 Conference Pioneer — AAAI 2019
🌉 Interdisciplinary Bridge — Artificial Intelligence and Deep Learning and Knowledge & Reasoning and Machine Learning
🧭 Keyword Pioneer — agent-environment system
🐣 Hot Topic Early Bird — formal verification
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio