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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Modern deep learning techniques have illustrated their excellent capabilitiesin many areas, but relies on large training data. Optimization-basedmeta-learning train a model on a variety tasks, such that it can solve newlearning tasks using only a small number of training samples.However, thesemethods assumes that training and test dataare identically and independentlydistributed. To overcome such limitation, in this paper, we propose invariantmeta learning for out-of-distribution tasks. Specifically, invariant metalearning find invariant optimal meta-initialization,and fast adapt toout-of-distribution tasks with regularization penalty. Extensive experimentsdemonstrate the effectiveness of our proposed invariant meta learning onout-of-distribution few-shot tasks.

Invariant Meta Learning for Out-of-Distribution Generalization