Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Self-Supervised GAN Compression

Jul 12, 2020
Chong Yu, Jeff Pool

* The appendix for this paper is in the following repository https://gitlab.com/dxxz/Self-Supervised-GAN-Compression-Appendix 

  Access Paper or Ask Questions

Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training

Jun 01, 2018
Maohua Zhu, Jason Clemons, Jeff Pool, Minsoo Rhu, Stephen W. Keckler, Yuan Xie


  Access Paper or Ask Questions

Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-Chip

Apr 26, 2018
Feiwen Zhu, Jeff Pool, Michael Andersch, Jeremy Appleyard, Fung Xie

* Published as a conference paper at ICLR 2018 

  Access Paper or Ask Questions

Efficient Sparse-Winograd Convolutional Neural Networks

Feb 18, 2018
Xingyu Liu, Jeff Pool, Song Han, William J. Dally

* Published as a conference paper at ICLR 2018 

  Access Paper or Ask Questions

Exploring the Regularity of Sparse Structure in Convolutional Neural Networks

Jun 05, 2017
Huizi Mao, Song Han, Jeff Pool, Wenshuo Li, Xingyu Liu, Yu Wang, William J. Dally

* submitted to NIPS 2017 

  Access Paper or Ask Questions

Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks

May 03, 2017
Minsoo Rhu, Mike O'Connor, Niladrish Chatterjee, Jeff Pool, Stephen W. Keckler


  Access Paper or Ask Questions

DSD: Dense-Sparse-Dense Training for Deep Neural Networks

Feb 21, 2017
Song Han, Jeff Pool, Sharan Narang, Huizi Mao, Enhao Gong, Shijian Tang, Erich Elsen, Peter Vajda, Manohar Paluri, John Tran, Bryan Catanzaro, William J. Dally

* Published as a conference paper at ICLR 2017 

  Access Paper or Ask Questions

Learning both Weights and Connections for Efficient Neural Networks

Oct 30, 2015
Song Han, Jeff Pool, John Tran, William J. Dally

* Published as a conference paper at NIPS 2015 

  Access Paper or Ask Questions