activity
20152022
most citedDoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

1.8k citations · 3.2k across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2017★ 17 cited

Learning to Run with Actor-Critic Ensemble

Zhewei Huang, Shuchang Zhou, BoEr Zhuang +1

We introduce an Actor-Critic Ensemble(ACE) method for improving the performance of Deep Deterministic Policy Gradient(DDPG) algorithm. At inference time, our method uses a critic e…

cs.LG2016★ 64 cited

Effective Quantization Methods for Recurrent Neural Networks

Qinyao He, He Wen, Shuchang Zhou +4

Reducing bit-widths of weights, activations, and gradients of a Neural Network can shrink its storage size and memory usage, and also allow for faster training and inference by exp…