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...
Prif Awduron: | Rao, D, Visin, F, Rusu, AA, Teh, YW, Pascanu, R, Hadsell, R |
---|---|
Fformat: | Conference item |
Cyhoeddwyd: |
Conference on Neural Information Processing Systems
2019
|
Eitemau Tebyg
-
Distral: robust multitask reinforcement learning
gan: Teh, YW, et al.
Cyhoeddwyd: (2017) -
Continuous hierarchical representations with poincaré Variational Auto-Encoder
gan: Mathieu,E, et al.
Cyhoeddwyd: (2019) -
Unsupervised learning of invariant representations
gan: Anselmi, Fabio, et al.
Cyhoeddwyd: (2018) -
Kalman contrastive unsupervised representation learning
gan: Mohammad Mahdi Jahani Yekta
Cyhoeddwyd: (2024-12-01) -
Unsupervised generative variational continual learning
gan: Liu, Guimeng
Cyhoeddwyd: (2023)