Skip to content

Training Deep Neural Networks using Block Coordinate Descent Algorithms

Notifications You must be signed in to change notification settings

timlautk/BCD-for-DNNs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

b85508f · Mar 6, 2018

History

73 Commits
Feb 6, 2018
Feb 6, 2018
Feb 6, 2018
Jan 26, 2018
Feb 6, 2018
Mar 6, 2018
Feb 12, 2018
Mar 6, 2018
Feb 8, 2018
Feb 12, 2018

Repository files navigation

BCD-for-DNNs

Codes for An Accelerated Block Coordinate Descent (BCD) Algorithm for Training Deep Neural Networks

For the BCD algorithms, MATLAB is used. Use MATLAB R2017a or later versions.

For the back propagation algorithms, Python (Jupyter Notebook) is used. Use TensorFlow 1.4 or later versions since Keras is included as a module in native TensorFlow 1.4 or later.

Two common datasets are used: MNIST and CIFAR-10

Download the CIFAR-10 dataset from: https://www.cs.toronto.edu/~kriz/cifar.html

About

Training Deep Neural Networks using Block Coordinate Descent Algorithms

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published