পদ্ধতির তুলনা করুন

	নলেজ ডিস্টিলেশন (Knowledge Distillation)	বিশেষজ্ঞদের মিশ্রণ
ক্ষেত্র	গভীর শিখন	গভীর শিখন
পরিবার	Machine learning	Machine learning
উদ্ভবের বছর	2015	2017
প্রবর্তক	Hinton, G., Vinyals, O. & Dean, J.	Shazeer, N. et al.
ধরন	Neural network compression (teacher–student)	Sparse neural network architecture (conditional computation)
মৌলিক উৎস	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538
অপর নাম	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
সম্পর্কিত	5	3
সারসংক্ষেপ	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.