Сравнение на методи

	Визуално контрастивно обучение	Смес от експерти
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2020	2017
Създател	Chen, T. et al. (SimCLR); He, K. et al. (MoCo)	Shazeer, N. et al.
Тип	Self-supervised deep representation learning	Sparse neural network architecture (conditional computation)
Основополагащ източник	Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. ICML.	Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538
Други названия	Karşıtlık Öğrenmesi — Görsel (SimCLR / MoCo / BYOL), contrastive learning, self-supervised visual representation learning, SimCLR	Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
Свързани	5	3
Резюме	Visual contrastive learning is a self-supervised deep-learning approach — popularised by frameworks such as SimCLR (Chen et al., 2020) and MoCo (He et al., 2020) — that learns rich image representations without labels by pulling different augmentations of the same image together and pushing different images apart. It turns a large pool of unlabelled images into a useful feature extractor.	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.