English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

One of the main motivations of studying continual learning is that theproblem setting allows a model to accrue knowledge from past tasks to learn newtasks more efficiently. However, recent studies suggest that the key metricthat continual learning algorithms optimize, reduction in catastrophicforgetting, does not correlate well with the forward transfer of knowledge. Webelieve that the conclusion previous works reached is due to the way theymeasure forward transfer. We argue that the measure of forward transfer to atask should not be affected by the restrictions placed on the continual learnerin order to preserve knowledge of previous tasks. Instead, forward transfershould be measured by how easy it is to learn a new task given a set ofrepresentations produced by continual learning on previous tasks. Under thisnotion of forward transfer, we evaluate different continual learning algorithmson a variety of image classification benchmarks. Our results indicate that lessforgetful representations lead to a better forward transfer suggesting a strongcorrelation between retaining past information and learning efficiency on newtasks. Further, we found less forgetful representations to be more diverse anddiscriminative compared to their forgetful counterparts.

Is forgetting less a good inductive bias for forward transfer?