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...
Główni autorzy: | Mathieu,E, Le Lan, C, Maddison, CJ, Tomioka, R, Teh, YW |
---|---|
Format: | Conference item |
Język: | English |
Wydane: |
Curran Associates
2019
|
Podobne zapisy
-
Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis
od: Marek Jakab, i wsp.
Wydane: (2020-12-01) -
VAEEG: Variational auto-encoder for extracting EEG representation
od: Tong Zhao, i wsp.
Wydane: (2024-12-01) -
Representation learning by hierarchical ELM auto‐encoder with double random hidden layers
od: Rui Li, i wsp.
Wydane: (2019-06-01) -
Learning Sparse Representation With Variational Auto-Encoder for Anomaly Detection
od: Jiayu Sun, i wsp.
Wydane: (2018-01-01) -
Hamiltonian Variational Auto-Encoder
od: Caterini, A, i wsp.
Wydane: (2019)