Click here to see all papers in nips2019
Gradient based sample selection for online continual learningEI
NeurIPS, pp. 11816-11825, 2019.
A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the previous data for the...More