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

We present a new "learning-to-learn"-type approach that enables rapidlearning of concepts from small-to-medium sized training sets and is primarilydesigned for web-initialized image retrieval. At the core of our approach is adeep architecture (a Set2Model network) that maps sets of examples to simplegenerative probabilistic models such as Gaussians or mixtures of Gaussians inthe space of high-dimensional descriptors. The parameters of the embedding intothe descriptor space are trained in the end-to-end fashion in the meta-learningstage using a set of training learning problems. The main technical novelty ofour approach is the derivation of the backprop process through the mixturemodel fitting, which makes the likelihood of the resulting modelsdifferentiable with respect to the positions of the input descriptors.  While the meta-learning process for a Set2Model network is discriminative, atrained Set2Model network performs generative learning of generative models inthe descriptor space, which facilitates learning in the cases when no negativeexamples are available, and whenever the concept being learned is polysemous orrepresented by noisy training sets. Among other experiments, we demonstratethat these properties allow Set2Model networks to pick visual concepts from theraw outputs of Internet image search engines better than a set of strongbaselines.

Set2Model Networks: Learning Discriminatively To Learn Generative Models