all AI news
Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning Approach. (arXiv:2207.06267v1 [cs.LG])
July 14, 2022, 1:12 a.m. | Prashant Bhat, Bahram Zonooz, Elahe Arani
cs.CV updates on arXiv.org arxiv.org
Continual learning (CL) over non-stationary data streams remains one of the
long-standing challenges in deep neural networks (DNNs) as they are prone to
catastrophic forgetting. CL models can benefit from self-supervised
pre-training as it enables learning more generalizable task-agnostic features.
However, the effect of self-supervised pre-training diminishes as the length of
task sequences increases. Furthermore, the domain shift between pre-training
data distribution and the task distribution reduces the generalizability of the
learned representations. To address these limitations, we propose Task …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote