...
机译:A 148-nW Reconfigurable Event-Driven Intelligent Wake-Up System for AIoT Nodes Using an Asynchronous Pulse-Based Feature Extractor and a Convolutional Neural Network
Beijing Laboratory of Future IC Technology and Science, School of Integrated Circuit, Peking University, Beijing, China;
Nano Core Company, Ltd., Hangzhou, China;
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China;
Power demand; Feature extraction; Task analysis; Erbium; Detectors; Neural networks; Convolutional neural networks; Always-on wake-up chip; artificial intelligence Internet of Things (AIoT); asynchronous; convolutional neural network (CNN); event-driven architecture; level-crossing (LC) analog-to-digital converter (ADC); random sparse event (RSE); reconfigurable; temporal-domain feature extraction;