README.md

Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks (NA)

This repository is the official implementation of Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks

Citation

@inproceedings{yang2021backpropagated,
  title={Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks},
  author={Yang, Yukun and Zhang, Wenrui and Li, Peng},
  booktitle={International Conference on Machine Learning},
  pages={11852--11862},
  year={2021},
  organization={PMLR}
}

Requirements

Dependencies and Libraries

• python 3.7
• pytorch
• torchvision

Installation

To install requirements:

pip install -r requirements.txt

Datasets

NMNIST: dataset, preprocessing

Training

Before running

Modify the data path and network settings in the config files.

Select the index of GPU in the main.py (0 by default)

Run the code

$ python main.py -config Networks/config_file.yaml
$ python main.py -config Networks/config_file.yaml -checkpoint checkpoint/ckpt.pth // load the checkpoint