CHAMP: Coherent Hardware-Aware Magnitude Pruning of Integrated Photonic Neural Networks

12/11/2021

∙

by   Sanmitra Banerjee, et al.

∙

0

∙

share

We propose a novel hardware-aware magnitude pruning technique for coherent photonic neural networks. The proposed technique can prune 99.45 parameters and reduce the static power consumption by 98.23 accuracy loss.