Sammenlign metoder

	Neural Architecture Search	Mixture of Experts
Fagområde	Dyb læring	Dyb læring
Familie	Machine learning	Machine learning
Oprindelsesår	2017	2017
Ophavsperson	Zoph, B. & Le, Q.V.	Shazeer, N. et al.
Type	Automated architecture optimization (deep learning)	Sparse neural network architecture (conditional computation)
Oprindelig kilde	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538
Aliasser	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
Relaterede	5	3
Resumé	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.	Mixture of Experts (MoE) is a sparse neural-network architecture, introduced by Shazeer and colleagues in 2017 with the sparsely-gated MoE layer, in which only a subset of expert sub-networks is activated for each input. As seen in models such as Switch Transformer and Mixtral, it holds computation cost fixed even as the total parameter count grows.