/dsbn_aistats2015

The Matlab Code for the AISTATS 2015 paper "Learning Deep Sigmoid Belief Network with Data Augmentation"

Primary LanguageMatlab

Deep Sigmoid Belief Network

The Matlab Code for the AISTATS 2015 paper "Learning Deep Sigmoid Belief Networks with Data Augmentation"

Zhe Gan (zhe.gan@duke.edu), Duke University, ECE department.

Introduction

This code implement the deep sigmoid belief network (DSBN), from the 2015 AISTATS paper with the same title. This source code is made publicly available for reproducibility purposes, it is not optimized for speed, minimally documented but fully functional.

License

Please note that this code should be used at your own risk. There is no implied guarantee that it will not do anything stupid. Permission is granted to use and modify the code.

Citing DSBN

Please cite our AISTATS paper in your publications if it helps your research:

@inproceedings{DSBN_AISTATS2015,
  Author = {Z. Gan, R. Henao, D. Carlson, and L. Carin},
  Title = {Learning Deep Sigmoid Belief Networks with Data Augmentation},
  booktitle={AISTATS},
  Year  = {2015}
}

Data

The datasets we used in the paper (.mat format files) can be downloaded from

https://drive.google.com/drive/u/0/folders/0B1HR6m3IZSO_SW1jS1ZtRXlpakU.