Variational Auto-Regressive Gaussian Processes for Continual Learning
Sanyam Kapoor 1 Theofanis Karaletsos 2 Thang D. Bui 3
Abstract
Through sequential construction of posteriors on
observing data online, Bayes’ theorem provides
a natural framework for continual learning. We
develop Variational Auto-Regressive Gaussian
Processes (VAR-GPs), a principled posterior up-
dating mechanism to solve sequential tasks in
continual learning. By relying on ...


雷达卡




京公网安备 11010802022788号







