research
∙
06/28/2022
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network
This work introduces the RevSilo, the first reversible module for bidire...
share
research
∙
04/19/2021
Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation
We propose combining memory saving techniques with traditional U-Net arc...
research
∙
07/02/2020
Adaptive Braking for Mitigating Gradient Delay
Neural network training is commonly accelerated by using multiple synchr...
research
∙
03/25/2020
Pipelined Backpropagation at Scale: Training Large Models without Batches
Parallelism is crucial for accelerating the training of deep neural netw...
research
∙
05/15/2019