TaxoNN: A Light-Weight Accelerator for Deep Neural Network Training
Abstract
Emerging intelligent embedded devices rely on Deep Neural Networks (DNNs) to be able to interact with the real-world environment. This interaction comes with the ability to retrain DNNs, since environmental conditions change continuously in time. Stochastic Gradient Descent (SGD) is a widely used algorithm to train DNNs by optimizing the parameters over the training data iteratively. In this work, first we present a novel approach to add the training ability to a baseline DNN accelerator (inference only) by splitting the SGD algorithm into simple computational elements. Then, based on this heuristic approach we propose TaxoNN, a light-weight accelerator for DNN training. TaxoNN can easily tune the DNN weights by reusing the hardware resources used in the inference process using a time-multiplexing approach and low-bitwidth units. Our experimental results show that TaxoNN delivers, on average, 0.97% higher misclassification rate compared to a full-precision implementation. Moreover, TaxoNN provides 2.1 power saving and 1.65 area reduction over the state-of-the-art DNN training accelerator.
Cite
@article{arxiv.2010.05197,
title = {TaxoNN: A Light-Weight Accelerator for Deep Neural Network Training},
author = {Reza Hojabr and Kamyar Givaki and Kossar Pourahmadi and Parsa Nooralinejad and Ahmad Khonsari and Dara Rahmati and M. Hassan Najafi},
journal= {arXiv preprint arXiv:2010.05197},
year = {2020}
}
Comments
Accepted to ISCAS 2020. 5 pages, 5 figures