CHAMP: Coherent Hardware-Aware Magnitude Pruning of Integrated Photonic Neural Networks
arXiv:2112.06098v110 citations
Originality Incremental advance
AI Analysis
This work addresses power efficiency for photonic neural networks, representing an incremental improvement in hardware-aware optimization.
The authors tackled the problem of reducing power consumption in photonic neural networks by introducing a hardware-aware magnitude pruning technique, achieving 99.45% parameter pruning and 98.23% static power reduction with minimal accuracy loss.
We propose a novel hardware-aware magnitude pruning technique for coherent photonic neural networks. The proposed technique can prune 99.45% of network parameters and reduce the static power consumption by 98.23% with a negligible accuracy loss.