1 code implementation • NeurIPS 2020 • Samuel Schoenholz, Ekin Dogus Cubuk
We introduce JAX MD, a software package for performing differentiable physics simulations with a focus on molecular dynamics.
no code implementations • NeurIPS 2019 • Yann N. Dauphin, Samuel Schoenholz
In particular, we find that this approach outperforms normalization for networks without skip connections on CIFAR-10 and can scale to Resnet-50 models on Imagenet.
no code implementations • NeurIPS 2017 • Ge Yang, Samuel Schoenholz
Classical feedforward neural networks, such as those with tanh activations, exhibit exponential behavior on the average when propagating inputs forward or gradients backward.