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

Gradient-based meta-learning methods leverage gradient descent to learn thecommonalities among various tasks. While previous such methods have beensuccessful in meta-learning tasks, they resort to simple gradient descentduring meta-testing. Our primary contribution is the {\em MT-net}, whichenables the meta-learner to learn on each layer's activation space a subspacethat the task-specific learner performs gradient descent on. Additionally, atask-specific learner of an {\em MT-net} performs gradient descent with respectto a meta-learned distance metric, which warps the activation space to be moresensitive to task identity. We demonstrate that the dimension of this learnedsubspace reflects the complexity of the task-specific learner's adaptationtask, and also that our model is less sensitive to the choice of initiallearning rates than previous gradient-based meta-learning methods. Our methodachieves state-of-the-art or comparable performance on few-shot classificationand regression tasks.

Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace