Variational Autoencoder (VAE)

A Variational Autoencoder is a type of likelihood-based generative model. It consists of an encoder, that takes in data $x$ as input and transforms this into a latent representation $z$, and a decoder, that takes a latent representation $z$ and returns a reconstruction $\hat{x}$. Inference is performed via variational inference to approximate the posterior of the model.
相关学科: AEcVAEVariational InferenceRepresentation LearningBeta-VAEGANImage GenerationText GenerationNormalizing FlowsVoice Conversion

学科讨论

讨论Icon

暂无讨论内容,你可以

推荐文献

按被引用数

学科管理组

暂无学科课代表,你可以申请成为课代表

重要学者

Yoshua Bengio

429868 被引用,1063 篇论文

Ilya Sutskever

165856 被引用,113 篇论文

Xiang Zhang

138753 被引用,2111 篇论文

Stephen M. Smith

128866 被引用,574 篇论文

Trevor Darrell

121211 被引用,688 篇论文

Jitendra Malik

118374 被引用,531 篇论文

Jay Hauser

117962 被引用,2529 篇论文

Bernhard Schölkopf

117502 被引用,1231 篇论文

Li Fei-Fei

116549 被引用,449 篇论文

Jürgen Schmidhuber

101619 被引用,563 篇论文