Login / Signup
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training.
Jianfei Chen
Lianmin Zheng
Zhewei Yao
Dequan Wang
Ion Stoica
Michael W. Mahoney
Joseph E. Gonzalez
Published in:
CoRR (2021)
Keyphrases
</>
training set
training phase
memory footprint
training data
real world
test set
training process
feedforward neural networks
genetic algorithm
social networks
feature selection
website
video sequences
evolutionary algorithm
hidden markov models
online learning
training samples
neural network
data sets