Repo

Deep-Mixture-of-Experts-via-Shallow-Embedding

@ryankim17920by Ryan Kim · Sophont

0

Unofficial PyTorch implementation of "Deep Mixture of Experts via Shallow Embedding" (arXiv:1806.01531), with CIFAR-10/100 training pipeline and analysis of gradient instabilities from the original paper.

Built withPython

See what other members are building and what each project is looking for.