/DGMM

Deep Generative Multi-view Model (DGMM)

Primary LanguagePython

Code for paper “Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning”

  • Authors: Changde Du, Changying Du, Lijie Huang, Huiguang He

This repository contains the implementation of the Deep Generative Multi-view Model (DGMM) described in Sharing deep generative representation for perceived image reconstruction from human brain activity and Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning.

Graphical models Illustration of the proposed DGMM framework Resluts

Dependencies

  • Keras
  • numpy
  • scipy
  • matlab

Usage

  • run the file DGMM_Keras.py directly.

Cite

Please cite our paper if you use this code in your own work:

@article{du2018reconstructing,
  title={Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning},
  author={Du, Changde and Du, Changying and Huang, Lijie and He, Huiguang},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2018}
}

@inproceedings{du2017sharing,
  title={Sharing deep generative representation for perceived image reconstruction from human brain activity},
  author={Du, Changde and Du, Changying and He, Huiguang},
  booktitle={IJCNN},
  year={2017}
}