A Review of Recent Advances of Binary Neural Networks for Edge Computing
This review paper aims to summarize the state-of-the-art in BNNs for researchers and practitioners working on efficient AI for edge computing devices.
This paper reviews recent advances in binary neural networks (BNNs) and 1-bit CNN technologies, which are suitable for edge computing. It classifies existing work based on various technical aspects and introduces their applications in computer vision and speech recognition.
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 paper reviews recent advances on binary neural network (BNN) and 1-bit CNN 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.