Continual learning for efficient machine learning

<p>Deep learning has enjoyed tremendous success over the last decade, but the training of practically useful deep models remains highly inefficient both in terms of the number of weight updates and training samples. To address one aspect of these issues, this thesis studies the continual learn...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awdur: Chaudhry, A
Awduron Eraill: Dokania, P
Fformat: Traethawd Ymchwil
Iaith:English
Cyhoeddwyd: 2020
Pynciau: