activity
20182022
most citedBayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning

165 citations · 318 across the 13 of their papers we have counts for

collaborators
Showing 2018Show all

2 papers · 1 filter

cond-mat.dis-nn2018★ 28 cited

Geometry of energy landscapes and the optimizability of deep neural networks

Simon Becker, Yao Zhang, Alpha A. Lee

Deep neural networks are workhorse models in machine learning with multiple layers of non-linear functions composed in series. Their loss function is highly non-convex, yet empiric…

cs.LG2018★ 56 cited

Energy-entropy competition and the effectiveness of stochastic gradient descent in machine learning

Yao Zhang, Andrew M. Saxe, Madhu S. Advani +1

Finding parameters that minimise a loss function is at the core of many machine learning methods. The Stochastic Gradient Descent algorithm is widely used and delivers state of the…