ScholarGate
Asistent

Porovnat metody

Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.

Automatické vyhledávání architektur neuronových sítí×Směs expertů×
OborHluboké učeníHluboké učení
RodinaMachine learningMachine learning
Rok vzniku20172017
TvůrceZoph, B. & Le, Q.V.Shazeer, N. et al.
TypAutomated architecture optimization (deep learning)Sparse neural network architecture (conditional computation)
Původní zdrojZoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗
Další názvyNöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture searchUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
Příbuzné53
ShrnutíNeural 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.
ScholarGateDatová sada
  1. v1
  2. 2 Zdroje
  3. PUBLISHED
  1. v1
  2. 2 Zdroje
  3. PUBLISHED

Přejít na hledání Stáhnout prezentaci

ScholarGatePorovnat metody: Neural Architecture Search · Mixture of Experts. Získáno 2026-06-19 z https://scholargate.app/cs/compare