Training Neural Networks for Execution on Approximate Hardware

Published in TinyML Research Symposium (TinyML), 2023

Recommended citation: Li, T., Li, S. and Gupta, P., 2023. Training Neural Networks for Execution on Approximate Hardware. arXiv preprint arXiv:2304.04125. https://arxiv.org/pdf/2304.04125.pdf

Proposed training optimizations to significantly improve the training time for neural networks to be executed on approximate hardware, including analog computing, stochastic computing, and approximate arithmetic.

Download paper here

BibTeX citation:

@article{li2023training, title={Training Neural Networks for Execution on Approximate Hardware}, author={Li, Tianmu and Li, Shurui and Gupta, Puneet}, journal={arXiv preprint arXiv:2304.04125}, year={2023} }