Uporedite metode

	MobileNet: Ефикасни конволуциони неуронски мреже за мобилску визију	Pretraga neuronske arhitekture	ResNet (Rezidualna Mreža)
Oblast	Duboko učenje	Duboko učenje	Duboko učenje
Porodica	Machine learning	Machine learning	Machine learning
Godina nastanka	2017	2017	2016
Tvorac	Andrew Howard et al. (Google)	Zoph, B. & Le, Q.V.	He, K.; Zhang, X.; Ren, S.; Sun, J.
Tip	Lightweight CNN architecture	Automated architecture optimization (deep learning)	Deep Convolutional Neural Network with skip connections
Temeljni izvor	Howard, A. G., et al. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint.	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.
Drugi nazivi	MobileNets, Depthwise Separable CNN, Efficient Mobile Vision Network, Mobil Evrişimli Sinir Ağı	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	ResNet, Residual Network, Deep Residual Learning, ResNet-50
Srodne	2	5	4
Sažetak	MobileNet is a family of lightweight convolutional neural network architectures introduced by Howard et al. at Google in 2017. It is designed to run image classification, object detection, and other vision tasks directly on mobile devices and embedded systems with limited computational budgets. By replacing standard convolutions with depthwise separable convolutions and exposing two global hyperparameters, MobileNet dramatically reduces multiply-add operations and model size while retaining competitive accuracy.	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.