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

We propose a new active learning strategy designed for deep neural networks.The goal is to minimize the number of data annotation queried from an oracleduring training. Previous active learning strategies scalable for deep networkswere mostly based on uncertain sample selection. In this work, we focus onexamples lying close to the decision boundary. Based on theoretical works onmargin theory for active learning, we know that such examples may help toconsiderably decrease the number of annotations. While measuring the exactdistance to the decision boundaries is intractable, we propose to rely onadversarial examples. We do not consider anymore them as a threat instead weexploit the information they provide on the distribution of the input space inorder to approximate the distance to decision boundaries. We demonstrateempirically that adversarial active queries yield faster convergence of CNNstrained on MNIST, the Shoe-Bag and the Quick-Draw datasets.

Adversarial Active Learning for Deep Networks: a Margin Based Approach