Reproduce “Multi-column Deep Neural Networks for Image Classification” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Dan Cireşan, Ueli Meier, Juergen Schmidhuber

The Multi-column deep neural network (MCDNN) classifies handwritten digits by training separate networks on differently normalized views and averaging their class predictions. Its MNIST test error is 0.23%, versus 0.44% ± 0.06 for the average of its individual networks. One network trained on all seven datasets reports 0.52%, but capacity and computation were not matched.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.