This is the official PyTorch implementation for Biologically inspired heterogeneous learning for accurate, efficient and low-latency neural network.
The paper has been accepted by National Science Review (NSR).
Install requirements by typing pip install -r requirements.txt.
- No special system requirements.
- The software has been tested on the Linux desktop (Ubuntu 20.04.3 LTS operation system) with Intel(R) Xeon(R) Gold 6226R CPU and NVIDIA Geforce RTX 3090 (Driver Version: 535.171.04, CUDA Version: 12.2).
Please cite our paper if you find it useful in your research:
@article{wang2024biologically,
title={Biologically inspired heterogeneous learning for accurate, efficient and low-latency neural network},
author={Wang, Bo and Zhang, Yuxuan and Li, Hongjue and Dou, Hongkun and Guo, Yuchen and Deng, Yue},
journal={National Science Review},
pages={nwae301},
year={2024},
publisher={Oxford University Press}
}
HIFI is released under the MIT License. See the LICENSE file for more details.