A Review of Recent Advances of Binary Neural Networks for Edge Computing

• Published in: IEEE journal on miniaturization for air and space systems Vol. 2; no. 1; pp. 25 - 35
• Main Authors: Zhao, Wenyu, Ma, Teli, Gong, Xuan, Zhang, Baochang, Doermann, David
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 1-bit convolutional neural network (CNN); Artificial intelligence; Artificial neural networks; binary neural network (BNN); Computer architecture; Computer vision; Convolutional neural networks; Edge computing; front-end computing; Industrial applications; neural architecture search; Neural networks; Optimization; Quantization (signal); Speech recognition; Tensors; Training; Unmanned aerial vehicles
• ISSN: 2576-3164; 2576-3164
• DOI: 10.1109/JMASS.2020.3034205

Edge computing is promising to become one of the next hottest topics in artificial intelligence because it benefits various evolving domains, such as real-time unmanned aerial systems, industrial applications, and the demand for privacy protection. This article reviews the recent advances on binary neural network (BNN) and 1-bit convolutional neural network technologies that are well suitable for front-end, edge-based computing. We introduce and summarize existing work and classify them based on gradient approximation, quantization, architecture, loss functions, optimization method, and binary neural architecture search. We also introduce applications in the areas of computer vision and speech recognition and discuss future applications for edge computing.