Suominen, Hanna

Last Name

Suominen

Hanna

Person

Now showing 1 - 1 of 1

Embargo
Learning to Continually Learn Rapidly from Few and Noisy Data
(ML Research Press, 2021) Kuo, Nicholas; Harandi, Mehrtash; Fourrier, N.; Walder, Christian; Ferraro, Gabriela; Suominen, Hanna
Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be achieved via replay { by concurrently training externally stored old data while learning a new task. However, replay becomes less effective when each past task is allocated with less memory. To overcome this difficulty, we supplemented replay mechanics with meta-learning for rapid knowledge acquisition. By employing a meta-learner, which learns a learn-ing rate per parameter per past task, we found that base learners produced strong results when less memory was available. Additionally, our approach inherited several meta-learning advantages for continual learning: it demonstrated strong robustness to continually learn under the presence of noises and yielded base learners to higher accuracy in less updates.