ScholarGate
Msaidizi

Linganisha mbinu

Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.

Mwanamfumo wa Kigeugeu wa Njia Nyingi×Mchanganyiko wa Wataalamu×
NyanjaUjifunzaji wa KinaUjifunzaji wa Kina
FamiliaMachine learningMachine learning
Mwaka wa asili20182017
MwanzilishiWu, M. and Goodman, N.Shazeer, N. et al.
AinaGenerative latent-variable modelSparse neural network architecture (conditional computation)
Chanzo asiliaWu, M., & Goodman, N. (2018). Multimodal Generative Models for Scalable Weakly-Supervised Learning. Advances in Neural Information Processing Systems (NeurIPS), 31. link ↗Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗
Majina mbadalaMVAE, multimodal VAE, multi-modal variational autoencoder, multimodal generative modelUzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts
Zinazohusiana33
MuhtasariThe 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.
ScholarGateSeti ya data
  1. v1
  2. 2 Vyanzo
  3. PUBLISHED
  1. v1
  2. 2 Vyanzo
  3. PUBLISHED

Nenda kwenye utafutaji Pakua slaidi

ScholarGateLinganisha mbinu: Multimodal Variational Autoencoder · Mixture of Experts. Imepatikana 2026-06-18 kutoka https://scholargate.app/sw/compare