This repository includes the official implementation of our NeurIPS 2022 Paper "Deep Differentiable Logic Gate Networks" (Paper @ ArXiv). The goal behind differentiable logic gate networks is to solve ...

By leveraging the Mish activation function’s advantages of smoothing non-monotonicities and providing more stable information propagation, the model’s gradient propagation during training is enhanced, ...

Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning Low-Rank Thinning Strengthen Out-of-Distribution Detection Capability with ...