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

Although deep neural networks are capable of achieving performance superiorto humans on various tasks, they are notorious for requiring large amounts ofdata and computing resources, restricting their success to domains where suchresources are available. Metalearning methods can address this problem bytransferring knowledge from related tasks, thus reducing the amount of data andcomputing resources needed to learn new tasks. We organize the MetaDLcompetition series, which provide opportunities for research groups all overthe world to create and experimentally assess new meta-(deep)learning solutionsfor real problems. In this paper, authored collaboratively between thecompetition organizers and the top-ranked participants, we describe the designof the competition, the datasets, the best experimental results, as well as thetop-ranked methods in the NeurIPS 2021 challenge, which attracted 15 activeteams who made it to the final phase (by outperforming the baseline), makingover 100 code submissions during the feedback phase. The solutions of the topparticipants have been open-sourced. The lessons learned include that learninggood representations is essential for effective transfer learning.

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone  fine-tuning without episodic meta-learning dominates for few-shot learning  image classification