The Deep Generative Decoder

DGD is a package for probabilistic representation learning. It can be applied to various tasks. The implementation for Fashion-MNIST and single-cell expression counts can be found in branch paper.

Installation

pip install git+https://github.com/Center-for-Health-Data-Science/dgd

Reference

If you use DGD in your research, please consider citing

@misc{https://doi.org/10.48550/arxiv.2110.06672,
  doi = {10.48550/ARXIV.2110.06672},
  
  url = {https://arxiv.org/abs/2110.06672},
  
  author = {Schuster, Viktoria and Krogh, Anders},
  
  keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {The deep generative decoder: Using MAP estimates of representations},
  
  publisher = {arXiv},
  
  year = {2021},
  
  copyright = {Creative Commons Attribution 4.0 International}
}