1.2k citations · 2.5k across the 17 of their papers we have counts for
3 papers · 1 filter
Learning Activation Functions to Improve Deep Neural Networks
Forest Agostinelli, Matthew Hoffman, Peter Sadowski +1
Artificial neural networks typically have a fixed, non-linear activation function at each neuron. We have designed a novel form of piecewise linear activation function that is lear…
Enhanced Higgs to Searches with Deep Learning
Pierre Baldi, Peter Sadowski, Daniel Whiteson
The Higgs boson is thought to provide the interaction that imparts mass to the fundamental fermions, but while measurements at the Large Hadron Collider (LHC) are consistent with t…
Searching for Exotic Particles in High-Energy Physics with Deep Learning
Pierre Baldi, Peter Sadowski, Daniel Whiteson
Collisions at high-energy particle colliders are a traditionally fruitful source of exotic particle discoveries. Finding these rare particles requires solving difficult signal-vers…