方法对比

	神经架构搜索	残差网络（ResNet）	迁移学习
领域	深度学习	深度学习	机器学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2017	2016	2010 (formalized); 1990s (early roots)
提出者	Zoph, B. & Le, Q.V.	He, K.; Zhang, X.; Ren, S.; Sun, J.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
类型	Automated architecture optimization (deep learning)	Deep Convolutional Neural Network with skip connections	Learning paradigm
开创性文献	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
别名	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	ResNet, Residual Network, Deep Residual Learning, ResNet-50	TL, domain adaptation, fine-tuning, pre-trained model adaptation
相关	5	4	3
摘要	Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All.	ResNet (Residual Network) is a deep convolutional neural network architecture introduced by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun at CVPR 2016. By inserting shortcut (skip) connections that carry the input of a block directly to its output — defining the block's task as learning a residual correction rather than a full mapping — ResNet enabled training of networks with hundreds or even thousands of layers without the vanishing-gradient degradation that had previously made very deep networks impractical. It won the ILSVRC 2015 image recognition competition with a top-5 error of 3.57% and remains the most widely used backbone architecture in computer vision.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.