no code implementations • 31 Jan 2022 • Brandon Paulsen, Chao Wang
The most scalable approaches to certifying neural network robustness depend on computing sound linear lower and upper bounds for the network's activation functions.
no code implementations • 21 Sep 2020 • Brandon Paulsen, Jingbo Wang, Jiawei Wang, Chao Wang
Unfortunately, existing methods either focus on verifying a single network or rely on loose approximations to prove the equivalence of two networks.
no code implementations • 20 Jul 2020 • Sara Mohammadinejad, Brandon Paulsen, Chao Wang, Jyotirmoy V. Deshmukh
As the memory footprint and energy consumption of such components become a bottleneck, there is interest in compressing and optimizing such networks using a range of heuristic techniques.
no code implementations • 10 Jan 2020 • Brandon Paulsen, Jingbo Wang, Chao Wang
Existing verification techniques such as Reluplex, ReluVal, and DeepPoly provide formal guarantees, but they are designed for analyzing a single network instead of the relationship between two networks.