深度殘差學習是由何愷明等人提出的。
Who invented deep residual learning?
September 29, 2025
作者: Juergen Schmidhuber
cs.AI
摘要
现代人工智能技术奠基于深度人工神经网络（NNs）。截至2025年，21世纪被引用次数最多的科学论文，便是一篇关于采用残差连接的深度残差学习的神经网络研究。那么，这一创新究竟出自谁手？本文将梳理深度残差学习发展的时间脉络。
English
Modern AI is based on deep artificial neural networks (NNs). As of 2025, the
most cited scientific article of the 21st century is an NN paper on deep
residual learning with residual connections. Who invented this? We present a
timeline of the evolution of deep residual learning.