数字农科院2.0

The Evolution of Convolutional Neural Network Architectures: A Review

文献类型： 外文期刊

作者： DEYONG MEI;JUNYI GONG;MINGDING QU; ;SHIQUAN BIAN1

关键词： Algorithms; architectures design; branch structure; convolutional neural networks; fundamental architectural components; underlying logic.

期刊名称： IEEE Access

ISSN： 2169-3536

年卷期： 2025 年

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Convolutional Neural Networks (CNNs) are one of the most important and successful algorithmic architectures in deep learning, especially effectively in processing data with a grid-like topological structure. Over the past decade, CNNs have demonstrated exceptional performance across various domains and continue to evolve actively as a major focus of research and development. The existing reviews on CNNs primarily provided either a broad overview or applications and implementations across specific areas, the contents of which in terms of the concepts, algorithms, and principles that underlying the fundamental architectural components often lack sufficient depth and breadth, providing only elementary introductions to a few conventional algorithms and models. In this review, we presented a comprehensive and systematic analysis of the algorithms and theoretical foundations that form the basis of the core building blocks for CNNarchitectures, covering convolutional algorithms, activation functions, spatial downsampling strategies, regularization techniques, normalization techniques, fully-connected layers, optimization algorithms, and classic CNN-based models. Our analysis specially emphasizes on the evolutionary trajectory of CNNs from the mathematical principles underlying the models and algorithms, which serves as a valuable complement to previous research efforts. By delving into the underlying logic of CNN architectures, we expect to provide a comprehensive framework rather than an overview for researchers who are interested in architectural innovation of CNNs. Furthermore, we investigated the current challenges and limitations of CNNs and proposed promising directions for future research.

分类号：

  • 相关文献

[1]Novel spectral indices and transfer learning model in estimat moisture status across winter wheat and summer maize. Li, Zongpeng,Cheng, Qian,Chen, Li,Zhai, Weiguang,Zhang, Bo,Mao, Bohan,Li, Yafeng,Ding, Fun,Zhou, Xinguo,Chen, Zhen. 2025

[2]Evolutionarily Informed Deep Learning Methods F.or Predicting Relative Transcript A bundance From Dna Sequence. Washburn, Jacob D.,Wang, Hai,Wang, Hai,Wang, Hai,Valluru, Ravi,Ramstein, Guillaume,Mejia-Guerra, Maria Katherine,Kremling, Karl A.,Wang, Hai,Buckler, Edward S.,Buckler, Edward S.. 2019

[3]Robust Graticule Intersection Localization For R.otated Topographic Maps. Dong, Luan,Dong, Luan,Zheng, Fengling,Yan, Qin,Zheng, Fengling,Dong, Luan,Dong, Luan. 2019

[4]3D Convolutional Neural Networks For C.rop Classification With Multi-Temporal R emote Sensing Images. Ji, SP, Zhang, C, Xu, AJ, Shi, Y, Duan, YL. 2018

作者其他论文 更多>>