Search Results for author: Roopsha Samanta

Found 2 papers, 1 papers with code

ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks

1 code implementation17 Jul 2019 Xuankang Lin, He Zhu, Roopsha Samanta, Suresh Jagannathan

Our key insight is that we can integrate an optimization-based abstraction refinement loop into the learning process and operate over dynamically constructed partitions of the input space that considers accuracy and safety objectives synergistically.

BIG-bench Machine Learning Collision Avoidance

Cannot find the paper you are looking for? You can Submit a new open access paper.