Continual Classification Learning Using Generative Models

  • Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain performance on previously learned tasks when tasks are presented one at a time. This problem is called catastrophic forgetting. In this work, we propose a classification model that learns continuously from sequentially observed tasks, while preventing catastrophic forgetting. We build on the lifelong generative capabilities of [10] and extend it to the classification setting by deriving a new variational bound on the joint log likelihood, $\log p(x; y)$.

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Frantzeska Lavda, Jason Ramapuram, Magda Gregorová, Alexandros Kalousis
DOI:https://doi.org/10.48550/arXiv.1810.10612
Parent Title (English):CoRR
Document Type:Article
Language:English
Year of publication:2018
Release Date:2024/01/22
Volume:abs/1810.10612
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.