The proceedings contain 53 papers. The topics discussed include: integrating present and past in unsupervised continual learning; partial models for building adaptive model-based reinforcement learning agents; probabilistic test-time generalization by variational neighbor-labeling; label augmentation for neural networks robustness; keep moving: identifying task-relevant subspaces to maximize plasticity for newly learned tasks; mitigating interference in the knowledge continuum through attention-guided incremental learning; stable update of regression trees; optimizing the learning rate for online training of neural networks; and towards diverse evaluation of class incremental learning: a representation learning perspective.
Lomonaco, V., Melacci, S., Tuytelaars, T., Chandar, S., Pascanu, R. (a cura di). (2024). Proceedings of The 3rd Conference on Lifelong Learning Agents. PMLR.
Proceedings of The 3rd Conference on Lifelong Learning Agents
Stefano Melacci;
2024-01-01
Abstract
The proceedings contain 53 papers. The topics discussed include: integrating present and past in unsupervised continual learning; partial models for building adaptive model-based reinforcement learning agents; probabilistic test-time generalization by variational neighbor-labeling; label augmentation for neural networks robustness; keep moving: identifying task-relevant subspaces to maximize plasticity for newly learned tasks; mitigating interference in the knowledge continuum through attention-guided incremental learning; stable update of regression trees; optimizing the learning rate for online training of neural networks; and towards diverse evaluation of class incremental learning: a representation learning perspective.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/1330255
