🚀 DEEP LEARNING PAPER OF THE WEEK Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, Shirley Ho Abstract "We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent representations when we train … Continue reading DLPOTW: DISCOVERING SYMBOLIC MODELS FROM DEEP LEARNING WITH INDUCTIVE BIASES