NeuralFlix
Sparse Training of Neural Networks Using AC/DC
Presenter: Damian Bogunowicz
This video summarizes deep learning research on the "Alternating Compressed/DeCompressed (AC/DC) training of DNNs."
AC/DC, a novel sparse training algorithm, allows you to prune your DNNs while still being trained, leading to simpler and quicker training workflows. AC/DC outperforms existing sparse training methods in accuracy, even at high sparsity levels. And in some cases, it creates even more accurate sparse networks than their dense counterparts.
This video covers the background on training-aware sparsification and what benefits it offers; a deep dive into the AC/DC algorithm, how it works, and the intuition behind it; and a walk-through of how to use AC/DC on your own models and deploy it for better performance and accuracy.