research
∙
06/09/2023
NuCLR: Nuclear Co-Learned Representations
We introduce Nuclear Co-Learned Representations (NuCLR), a deep learning...
share
research
∙
09/30/2022
Finding NEEMo: Geometric Fitting using Neural Estimation of the Energy Mover's Distance
A novel neural architecture was recently developed that enforces an exac...
research
∙
05/20/2022
Towards Understanding Grokking: An Effective Theory of Representation Learning
We aim to understand grokking, a phenomenon where models generalize long...
research
∙
11/30/2021