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

Add code
Dec 11, 2021
Sanmitra Banerjee, Mahdi Nikdast, Sudeep Pasricha, Krishnendu Chakrabarty
Figure 1 for CHAMP: Coherent Hardware-Aware Magnitude Pruning of Integrated Photonic Neural Networks
Figure 2 for CHAMP: Coherent Hardware-Aware Magnitude Pruning of Integrated Photonic Neural Networks
Figure 3 for CHAMP: Coherent Hardware-Aware Magnitude Pruning of Integrated Photonic Neural Networks

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

* This paper has been accepted for oral presentation at the IEEE/OPTICA Optical Fiber Communication Conference (OFC) 2022 and will appear in OFC proceedings  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon