2021.08.25
Cutting “Edge”: A Tunable Neural Network Framework Towards Compact and Efficient Models
Convolutional neural networks (CNNs) have enabled numerous AI-enhanced applications, such as image recognition. However, the implementation of state-of-the-art CNNs on low-power edge devices of Internet-of-Things (IoT) networks is challenging because of large resource requirements. Researchers from Tokyo Institute of Technology have now solved this problem with their efficient sparse CNN processor architecture and training algorithms that enable seamless integration of CNN models on edge devices.
