A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural Networks

no code implementations • 11 Mar 2022 • Christopher Lazarus, Mykel J. Kochenderfer

We compare the runtime of our approach against state-of-the-art verification algorithms for full-precision neural networks.

Collision Avoidance Model Compression

Deep Binary Reinforcement Learning for Scalable Verification

no code implementations • 11 Mar 2022 • Christopher Lazarus, Mykel J. Kochenderfer

We present an RL algorithm tailored specifically for BNNs.

reinforcement-learning Reinforcement Learning (RL)

Runtime Safety Assurance Using Reinforcement Learning

no code implementations • 20 Oct 2020 • Christopher Lazarus, James G. Lopez, Mykel J. Kochenderfer

The airworthiness and safety of a non-pedigreed autopilot must be verified, but the cost to formally do so can be prohibitive.

reinforcement-learning Reinforcement Learning (RL)

Algorithms for Verifying Deep Neural Networks

2 code implementations • 15 Mar 2019 • Changliu Liu, Tomer Arnon, Christopher Lazarus, Clark Barrett, Mykel J. Kochenderfer

Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control.