ScholarGate
アシスタント

手法を比較

選択した手法を並べて確認できます。異なる行はハイライト表示されます。

知識蒸留×混合専門家モデル×
分野深層学習深層学習
系統Machine learningMachine learning
提唱年20152017
提唱者Hinton, G., Vinyals, O. & Dean, J.Shazeer, N. et al.
種類Neural network compression (teacher–student)Sparse neural network architecture (conditional computation)
原典Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗
別名Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
関連53
概要Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.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.
ScholarGateデータセット
  1. v1
  2. 2 出典
  3. PUBLISHED
  1. v1
  2. 2 出典
  3. PUBLISHED

検索へ スライドをダウンロード

ScholarGate手法を比較: Knowledge Distillation · Mixture of Experts. 2026-06-18に以下より取得 https://scholargate.app/ja/compare