Papers of the day   All papers

Functional Regularisation for Continual Learning

Comments

Jun 18 2019 DeepMind

Neural networks suffer from catastrophic forgetting when tasks are encountered sequentially. We overcome this by Bayesian inference in function space, using inducing point sparse GP methods and by optimising over rehearsal data points: http://arxiv.org/abs/1901.11356 https://t.co/lMvXZxPG7r
8 replies, 882 likes


Content