Efficient Training Convolutional Neural Networks on Edge Devices with Gradient-pruned Sign-symmetric Feedback Alignment

Abstract

With the prosperity of mobile devices, the distributed learning approach enabling model training with decentralized data has attracted wide research. However, the lack of training capability for edge devices significantly limits the energy efficiency of distributed learning in real life. This paper describes a novel approach of training DNNs exploiting the redundancy and the weight asymmetry potential of conventional backpropagation. We demonstrate that with negligible classification accuracy loss, the proposed approach outperforms the prior arts by 5x in terms of energy efficiency.

This work is published in the Proceedings of the 9th International Conference on IT Convergence and Security (ICITCS2021)

References in corpus (2)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Random feedback weights support learning in deep neural networks