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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Joel Hestness

Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation


Apr 21, 2021
Mihir Pendse, Vithursan Thangarasa, Vitaliy Chiley, Ryan Holmdahl, Joel Hestness, Dennis DeCoste

* Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (2021) 388-397 
* 11 pages, 5 figures, Published at MICCAI Brainles 2020 

  Access Paper or Ask Questions

Pipelined Backpropagation at Scale: Training Large Models without Batches


Mar 25, 2020
Atli Kosson, Vitaliy Chiley, Abhinav Venigalla, Joel Hestness, Urs Köster


  Access Paper or Ask Questions

Compositional Generalization for Primitive Substitutions


Oct 07, 2019
Yuanpeng Li, Liang Zhao, Jianyu Wang, Joel Hestness

* EMNLP 2019 

  Access Paper or Ask Questions

Beyond Human-Level Accuracy: Computational Challenges in Deep Learning


Sep 03, 2019
Joel Hestness, Newsha Ardalani, Greg Diamos


  Access Paper or Ask Questions

Deep Learning Scaling is Predictable, Empirically


Dec 01, 2017
Joel Hestness, Sharan Narang, Newsha Ardalani, Gregory Diamos, Heewoo Jun, Hassan Kianinejad, Md. Mostofa Ali Patwary, Yang Yang, Yanqi Zhou

* 19 pages, 11 figures 

  Access Paper or Ask Questions

Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting


Jul 04, 2017
Sercan O. Arik, Markus Kliegl, Rewon Child, Joel Hestness, Andrew Gibiansky, Chris Fougner, Ryan Prenger, Adam Coates

* Accepted to Interspeech 2017 

  Access Paper or Ask Questions