hehaodele / SBL-LSTM-Net

[NeurIPS 2017][Oral] From Bayesian Sparsity to Gated Recurrent Nets

SBL-LSTM-Net

This is the original implementation of the deep nerual network model proposed in our paper, "From Bayesian Sparsity to Gated Recurrent Nets"[Paper].

If you find this code useful in your research, please cite:

@article{he2017bayesian,
  title={From Bayesian Sparsity to Gated Recurrent Nets},
  author={He, Hao and Xin, Bo and Wipf, David},
  journal={arXiv preprint arXiv:1706.02815},
  year={2017}
}

Requirements

• Linux or macOS
• Torch 7
• Python 2 or 3
• CPU or NVIDIA GPU + CUDA CuDNN

Get started

Train/Test