A multi-agent reinforcement learning based approach for automatic filter pruning

A multi-agent reinforcement learning based approach for automatic filter pruning

Abstract Deep Convolutional Neural Networks (DCNNs), due to their high computational and memory requirements, face significant challenges in deployment on resource-constrained devices. Network Pruning, an essential model compression technique, contributes to enabling the efficient deployment of DCNN...

Ful tanımlama

Detaylı Bibliyografya
Asıl Yazarlar: Zhemin Li, Xiaojing Zuo, Yiping Song, Dong Liang, Zheng Xie
Materyal Türü: Makale
Dil:English
Baskı/Yayın Bilgisi: Nature Portfolio 2024-12-01
Seri Bilgileri:Scientific Reports
Konular:
Filter pruning
QMIX algorithm
Knowledge distillation
Online Erişim:https://doi.org/10.1038/s41598-024-82562-w

Internet

https://doi.org/10.1038/s41598-024-82562-w

Benzer Materyaller