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 Knowledge & Reasoning
🐣
Hot Topic Early Bird
- formal verification
Topics
Artificial Intelligence > Core AI > Agent Systems
Artificial Intelligence > Core AI > AI Safety
Artificial Intelligence > Core AI > Interpretability
Machine Learning > Optimization & Theory > Theory
Deep Learning > Architectures > Neural Networks
Knowledge & Reasoning > Reasoning > Formal Methods
Machine Learning > Core Methods > Interpretability