Сравнение методов

	Дифференциальная эволюция	Нейросетевой поиск архитектур
Область	Оптимизация	Глубокое обучение
Семейство	Process / pipeline	Machine learning
Год появления	1997	2017
Автор метода	Rainer Storn & Kenneth Price	Zoph, B. & Le, Q.V.
Тип	Population-based stochastic metaheuristic	Automated architecture optimization (deep learning)
Основополагающий источник	Storn, R. & Price, K. (1997). Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces. Journal of Global Optimization, 11(4), 341–359.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.
Другие названия	DE algorithm, Diferansiyel Evrim (DE), DE optimization	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Связанные	5	5
Сводка	Differential Evolution (DE), introduced by Rainer Storn and Kenneth Price in 1997, is a population-based stochastic optimisation algorithm designed for continuous parameter spaces. It generates candidate solutions by combining vector differences between existing population members, making it a powerful and parameter-lean alternative to Genetic Algorithms and Particle Swarm Optimisation when the search landscape is non-convex, multimodal, or poorly suited to gradient-based methods.	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.