Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to content

LiQianxiao/discrete-MSA

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
LICENSE.md
LICENSE.md
 
 
README.md
README.md
 
 
cifar10.py
cifar10.py
 
 
cifar10_conv_binary.ipynb
cifar10_conv_binary.ipynb
 
 
cifar10_conv_ternary.ipynb
cifar10_conv_ternary.ipynb
 
 
dataset.py
dataset.py
 
 
download.py
download.py
 
 
layers.py
layers.py
 
 
mnist_fc_binary.ipynb
mnist_fc_binary.ipynb
 
 
mnist_fc_ternary.ipynb
mnist_fc_ternary.ipynb
 
 
network.py
network.py
 
 
read_cifar10_data.py
read_cifar10_data.py
 
 
svhn_conv_binary.ipynb
svhn_conv_binary.ipynb
 
 
svhn_conv_ternary.ipynb
svhn_conv_ternary.ipynb
 
 
train.py
train.py
 
 
utils.py
utils.py
 
 

Repository files navigation

Discrete Method of Successive Approximations

Tensorflow implementations of the discrete method of successive approximations.

Paper: Qianxiao Li and Shuji Hao. "An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks". The 35th International Conference on Machine Learning, 2018

URL: http://proceedings.mlr.press/v80/li18b.html

Examples

  • Various examples reproducing results in the paper are in the Jupyter notebook files

Authors

License

This project is licensed under GPL v3 - see the LICENSE.md file for details

About

No description, website, or topics provided.

Resources

Readme

License

GPL-3.0 license
Activity

Stars

20 stars

Watchers

5 watching

Forks

7 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages