Uporedite metode

	MobileNet: Ефикасни конволуциони неуронски мреже за мобилску визију	Pretraga neuronske arhitekture	Transferno učenje
Oblast	Duboko učenje	Duboko učenje	Mašinsko učenje
Porodica	Machine learning	Machine learning	Machine learning
Godina nastanka	2017	2017	2010 (formalized); 1990s (early roots)
Tvorac	Andrew Howard et al. (Google)	Zoph, B. & Le, Q.V.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Tip	Lightweight CNN architecture	Automated architecture optimization (deep learning)	Learning paradigm
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.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
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	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Srodne	2	5	3
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.	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.