השוואת שיטות

	מפענח אוטומטי וריאציוני רב-אופני	תערובת מומחים
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2018	2017
הוגה השיטה	Wu, M. and Goodman, N.	Shazeer, N. et al.
סוג	Generative latent-variable model	Sparse neural network architecture (conditional computation)
מקור מכונן	Wu, M., & Goodman, N. (2018). Multimodal Generative Models for Scalable Weakly-Supervised Learning. Advances in Neural Information Processing Systems (NeurIPS), 31.	Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538
כינויים	MVAE, multimodal VAE, multi-modal variational autoencoder, multimodal generative model	Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
קשורות	3	3
תקציר	The Multimodal Variational Autoencoder (MVAE) is a deep generative model that learns a shared latent representation across two or more data modalities — such as images and captions — using a product-of-experts fusion of modality-specific encoders, enabling generation and inference even when only a subset of modalities is observed at test time.	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.