A quantitative analysis of how the Variational Continual Learning method handles catastrophic forgetting
Catastrophic forgetting is a problem that occurs when an artificial neural network in the continual learning setting replaces historic information as additional information is acquired. Several methods claiming to handle the aforementioned problem are trained and evaluated using data sets with a sma...
Main Authors: | , |
---|---|
Format: | Others |
Language: | English |
Published: |
KTH, Skolan för elektroteknik och datavetenskap (EECS)
2020
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-280447 |