Constrained Feedforward Neural Network Training via Reachability Analysis
Chung, Long Kiu, Dai, Adam, Knowles, Derek, Kousik, Shreyas, Gao, Grace X.
–arXiv.org Artificial Intelligence
Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge to train a neural network to obey safety constraints. Most existing safety-related methods only seek to verify that already-trained networks obey constraints, requiring alternating training and verification. Instead, this work proposes a constrained method to simultaneously train and verify a feedforward neural network with rectified linear unit (ReLU) nonlinearities. Constraints are enforced by computing the network's output-space reachable set and ensuring that it does not intersect with unsafe sets; training is achieved by formulating a novel collision-check loss function between the reachable set and unsafe portions of the output space. The reachable and unsafe sets are represented by constrained zonotopes, a convex polytope representation that enables differentiable collision checking. The proposed method is demonstrated successfully on a network with one nonlinearity layer and approximately 50 parameters.
arXiv.org Artificial Intelligence
Jul-16-2021
- Country:
- North America > United States > California > Santa Clara County (0.14)
- Genre:
- Research Report (0.40)
- Technology: