Zhiming Liu

Learning safe neural network controllers with barrier certificates

2021 · Formal Aspects of Computing

Abstract We provide a new approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier …

Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models

2020 · arXiv (Cornell University)

Recent research has revealed that deep generative models including flow-based models and Variational Autoencoders may assign higher likelihoods to out-of-distribution (OOD) data than in-distribution (ID) data. However, we cannot sample OOD data from the model. …