Back to Search
Start Over
Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence
- Source :
- Nature Machine Intelligence, 2, 43-55 (2020)
- Publication Year :
- 2019
-
Abstract
- The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles. Quantization is a powerful tool to address the growing computational cost of such applications, and yields significant compression over full-precision networks. However, quantization can result in substantial loss of performance for complex image classification tasks. To address this, we propose a Principal Component Analysis (PCA) driven methodology to identify the important layers of a binary network, and design mixed-precision networks. The proposed Hybrid-Net achieves a more than 10% improvement in classification accuracy over binary networks such as XNOR-Net for ResNet and VGG architectures on CIFAR-100 and ImageNet datasets while still achieving up to 94% of the energy-efficiency of XNOR-Nets. This work furthers the feasibility of using highly compressed neural networks for energy-efficient neural computing in edge devices.<br />Comment: 14 pages, 4 figures, 8 tables
Details
- Database :
- arXiv
- Journal :
- Nature Machine Intelligence, 2, 43-55 (2020)
- Publication Type :
- Report
- Accession number :
- edsarx.1906.01493
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1038/s42256-019-0134-0