15 citations · 38 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2019★ 15 cited
The Search for Sparse, Robust Neural Networks
Justin Cosentino, Federico Zaiter, Dan Pei +1
Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters…
cs.LG2019★ 2 cited
Generative Well-intentioned Networks
Justin Cosentino, Jun Zhu
We propose Generative Well-intentioned Networks (GWINs), a novel framework for increasing the accuracy of certainty-based, closed-world classifiers. A conditional generative networ…