Continual unsupervised representation learning
Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised or reinforcement learning tasks, and often assumes full knowl...
Príomhchruthaitheoirí: | Rao, D, Visin, F, Rusu, AA, Teh, YW, Pascanu, R, Hadsell, R |
---|---|
Formáid: | Conference item |
Foilsithe / Cruthaithe: |
Conference on Neural Information Processing Systems
2019
|
Míreanna comhchosúla
Míreanna comhchosúla
-
Distral: robust multitask reinforcement learning
de réir: Teh, YW, et al.
Foilsithe / Cruthaithe: (2017) -
Continuous hierarchical representations with poincaré Variational Auto-Encoder
de réir: Mathieu,E, et al.
Foilsithe / Cruthaithe: (2019) -
Unsupervised learning of invariant representations
de réir: Anselmi, Fabio, et al.
Foilsithe / Cruthaithe: (2018) -
Kalman contrastive unsupervised representation learning
de réir: Mohammad Mahdi Jahani Yekta
Foilsithe / Cruthaithe: (2024-12-01) -
Unsupervised generative variational continual learning
de réir: Liu, Guimeng
Foilsithe / Cruthaithe: (2023)