Learning to Prune Deep Neural Networks via Reinforcement Learning

no code implementations • 9 Jul 2020 • Manas Gupta, Siddharth Aravindan, Aleksandra Kalisz, Vijay Chandrasekhar, Lin Jie

PuRL achieves more than 80% sparsity on the ResNet-50 model while retaining a Top-1 accuracy of 75. 37% on the ImageNet dataset.

Model Compression reinforcement-learning +1