Less is more: Efficient pruning for reducing AI memory and computational cost

https://www.eurekalert.org/news-releases/1087244

"better understanding of the mechanism underlying successful deep learning leads to an efficient pruning of unnecessary parameters in a deep architecture without affecting its performance. It all hinges on an initial understanding of what happens in deep networks, how they learn and what parameters are essential to its learning... prune up to 90% certain layers' parameters without hindering system’s accuracy... better AI systems memory usage/ energy consumption"