Σύγκριση μεθόδων

	NEAT: Νευροεξέλιξη Αυξανόμενων Τοπολογιών	Στρατηγική Εξέλιξης (CMA-ES)	Αναζήτηση Νευρωνικής Αρχιτεκτονικής
Πεδίο	Βαθιά Μάθηση	Βελτιστοποίηση	Βαθιά Μάθηση
Οικογένεια	Machine learning	Process / pipeline	Machine learning
Έτος προέλευσης	2002	2001	2017
Δημιουργός	Kenneth Stanley & Risto Miikkulainen	Nikolaus Hansen & Andreas Ostermeier	Zoph, B. & Le, Q.V.
Τύπος	Neuroevolutionary algorithm	Derivative-free continuous black-box optimizer	Automated architecture optimization (deep learning)
Θεμελιώδης πηγή	Stanley, K. O., & Miikkulainen, R. (2002). Evolving neural networks through augmenting topologies. Evolutionary Computation, 10(2), 99–127.	Hansen, N. & Ostermeier, A. (2001). Completely Derandomized Self-Adaptation in Evolutionary Strategies. Evolutionary Computation, 9(2), 159-195.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.
Εναλλακτικές ονομασίες	Neuroevolution of Augmenting Topologies, Topology and Weight Evolving Artificial Neural Networks (variant), Evolving Neural Networks, Topoloji Artırımlı Nöroevrim	CMA-ES, Evolution Strategy, Evrimsel Strateji (CMA-ES), self-adapting evolution strategy	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
Συναφείς	3	5	5
Σύνοψη	NEAT is a genetic algorithm for evolving artificial neural networks introduced by Kenneth Stanley and Risto Miikkulainen in 2002. Unlike methods that evolve weights alone, NEAT simultaneously evolves both the topology (structure) and the connection weights of neural networks. It achieves this through a direct genome encoding with historical markings that enable meaningful crossover between networks of different structures, making it applicable to reinforcement learning, game playing, and control tasks without requiring a predefined architecture.	CMA-ES, short for Covariance Matrix Adaptation Evolution Strategy, is a modern derivative-free optimizer for continuous black-box functions introduced by Hansen and Ostermeier in 2001. It maintains a population of candidate solutions drawn from a multivariate normal distribution and iteratively updates the distribution's mean, step size, and full covariance matrix to steer the search toward better regions of the parameter space. It has become the de-facto standard for continuous black-box optimization and is widely used in neural architecture search and reinforcement-learning policy optimization.	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.