Continually Learning Self-Supervised Representations with Projected Functional Regularization.
Alex Gomez-VillaBartlomiej TwardowskiLu YuAndrew D. BagdanovJoost van de WeijerPublished in: CoRR (2021)
Keyphrases
- learning process
- learning algorithm
- learning systems
- multi view learning
- inductive learning
- background knowledge
- unsupervised learning
- knowledge acquisition
- higher level
- supervised learning
- prior knowledge
- reinforcement learning
- learning tasks
- incremental learning
- case study
- multiple representations
- machine learning