Continuous hierarchical representations with poincaré Variational Auto-Encoder
The Variational Auto-Encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot efficiently embed tree-like structures. Hyperbolic spaces w...
Päätekijät: | Mathieu,E, Le Lan, C, Maddison, CJ, Tomioka, R, Teh, YW |
---|---|
Aineistotyyppi: | Conference item |
Kieli: | English |
Julkaistu: |
Curran Associates
2019
|
Samankaltaisia teoksia
-
Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis
Tekijä: Marek Jakab, et al.
Julkaistu: (2020-12-01) -
VAEEG: Variational auto-encoder for extracting EEG representation
Tekijä: Tong Zhao, et al.
Julkaistu: (2024-12-01) -
Representation learning by hierarchical ELM auto‐encoder with double random hidden layers
Tekijä: Rui Li, et al.
Julkaistu: (2019-06-01) -
Learning Sparse Representation With Variational Auto-Encoder for Anomaly Detection
Tekijä: Jiayu Sun, et al.
Julkaistu: (2018-01-01) -
Hamiltonian Variational Auto-Encoder
Tekijä: Caterini, A, et al.
Julkaistu: (2019)