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

In this work, we perform unsupervised learning of representations bymaximizing mutual information between an input and the output of a deep neuralnetwork encoder. Importantly, we show that structure matters: incorporatingknowledge about locality of the input to the objective can greatly influence arepresentation's suitability for downstream tasks. We further controlcharacteristics of the representation by matching to a prior distributionadversarially. Our method, which we call Deep InfoMax (DIM), outperforms anumber of popular unsupervised learning methods and competes withfully-supervised learning on several classification tasks. DIM opens newavenues for unsupervised learning of representations and is an important steptowards flexible formulations of representation-learning objectives forspecific end-goals.

Learning deep representations by mutual information estimation and maximization