SeoulTech-HCIRLab/LSTCM

New RNN Activation Technique forDeeper Networks: LSTCM cells

This repository contains the experiments done in the work New RNN Activation Technique for Deeper Networks: LSTCM Cells by Soo-Han Kang and Ji-Hyeong Han

@article{kang2020new,
  title={New RNN Activation Technique for Deeper Networks: LSTCM Cells},
  author={Kang, Soo-Han and Han, Ji-Hyeong},
  journal={IEEE Access},
  volume={8},
  pages={214625--214632},
  year={2020},
  publisher={IEEE}
}

Requirements

• NumPy >= 1.11.1
• TensorFlow >= 1.3
• tqdm
• matplotlib

Data

We train the model on Penn Tree Bank datasets. site[https://catalog.ldc.upenn.edu/LDC99T42]

Training

  * python train.py