Compara mètodes

	Cerca d'Arquitectures Neuronals	Optimització estocàstica
Camp	Aprenentatge profund	Optimització
Família	Machine learning	Process / pipeline
Any d'origen	2017	1951 (SGD); 2014 (Adam)
Autor original	Zoph, B. & Le, Q.V.	—
Tipus	Automated architecture optimization (deep learning)	Gradient-based iterative optimization
Font seminal	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. Annals of Mathematical Statistics, 22(3), 400-407.
Àlies	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	Stokastik Optimizasyon (SGD & Varyantları), stochastic gradient descent, SGD, Adam
Relacionats	5	3
Resum	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.	Stochastic optimization is a family of iterative methods that minimize an objective function by computing gradients on randomly sampled subsets of data — mini-batches — rather than on the entire dataset at once. Pioneered by Robbins and Monro in 1951 as stochastic approximation, the approach became the standard engine for training large-scale machine-learning models through variants such as SGD with momentum, AdaGrad, RMSProp, and Adam.