方法对比

	NEAT：拓扑增强神经进化	进化策略（CMA-ES）	遗传算法	神经架构搜索
领域	深度学习	优化	优化	深度学习
方法族	Machine learning	Process / pipeline	Process / pipeline	Machine learning
起源年份	2002	2001	1975	2017
提出者	Kenneth Stanley & Risto Miikkulainen	Nikolaus Hansen & Andreas Ostermeier	John Henry Holland	Zoph, B. & Le, Q.V.
类型	Neuroevolutionary algorithm	Derivative-free continuous black-box optimizer	Population-based metaheuristic	Automated architecture optimization (deep learning)
开创性文献	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.	Holland, J.H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.
别名	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	GA, evolutionary algorithm, Genetik Algoritma — Evrimsel Optimizasyon	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search
相关	3	5	5	5
摘要	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.	A genetic algorithm (GA) is a population-based metaheuristic optimization method introduced by John Henry Holland (1975) that mimics the principles of natural selection. It maintains a population of candidate solutions and iteratively improves them through selection, crossover, and mutation operators, making it especially powerful on discontinuous, non-convex, and multi-modal search spaces where classical gradient-based methods fail.	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.