PyTorch Implementation of “Unsupervised learning by competing hidden units” MNIST classifier
This reprository is a PyTorch implementation of the paper "Unsupervised learning by competing hidden units". By Dmitry Krotov and John J. Hopfield.
We also very brielfy explore adversarial robustness of models implemented with this method.
Thanks to both original authors for such a unique and fascinating area of exploration.
For a more detailed explanation please see this post.