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

Polythetic classifications, based on shared patterns of features that needneither be universal nor constant among members of a class, are common in thenatural world and greatly outnumber monothetic classifications over a set offeatures. We show that threshold meta-learners, such as Prototypical Networks,require an embedding dimension that is exponential in the number oftask-relevant features to emulate these functions. In contrast, attentionalclassifiers, such as Matching Networks, are polythetic by default and able tosolve these problems with a linear embedding dimension. However, we find thatin the presence of task-irrelevant features, inherent to meta-learningproblems, attentional models are susceptible to misclassification. To addressthis challenge, we propose a self-attention feature-selection mechanism thatadaptively dilutes non-discriminative features. We demonstrate theeffectiveness of our approach in meta-learning Boolean functions, and syntheticand real-world few-shot learning tasks.

Attentional Meta-learners for Few-shot Polythetic Classification