all AI news
Class-Incremental Continual Learning into the eXtended DER-verse. (arXiv:2201.00766v1 [cs.LG])
Jan. 4, 2022, 2:10 a.m. | Matteo Boschini, Lorenzo Bonicelli, Pietro Buzzega, Angelo Porrello, Simone Calderara
cs.LG updates on arXiv.org arxiv.org
The staple of human intelligence is the capability of acquiring knowledge in
a continuous fashion. In stark contrast, Deep Networks forget catastrophically
and, for this reason, the sub-field of Class-Incremental Continual Learning
fosters methods that learn a sequence of tasks incrementally, blending
sequentially-gained knowledge into a comprehensive prediction.
This work aims at assessing and overcoming the pitfalls of our previous
proposal Dark Experience Replay (DER), a simple and effective approach that
combines rehearsal and Knowledge Distillation. Inspired by the way …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Director, Global Procurement Data Analytics
@ Alcon | Fort Worth - Main
Backend Software Engineer, Airbnb for Real Estate
@ Airbnb | United States
Data Scientist
@ Exoticca | Barcelona, Catalonia, Spain - Remote
ESG Data Analytics Summer Associate (Intern)
@ Apex Clean Energy | Charlottesville, VA, United States
Team Lead, Machine Learning
@ Prenuvo | Vancouver, British Columbia, Canada