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

Building robust online content recommendation systems requires learningcomplex interactions between user preferences and content features. The fieldhas evolved rapidly in recent years from traditional multi-arm bandit andcollaborative filtering techniques, with new methods employing Deep Learningmodels to capture non-linearities. Despite progress, the dynamic nature ofonline recommendations still poses great challenges, such as finding thedelicate balance between exploration and exploitation. In this paper we showhow uncertainty estimations can be incorporated by employing them in anoptimistic exploitation/exploration strategy for more efficient exploration ofnew recommendations. We provide a novel hybrid deep neural network model, DeepDensity Networks (DDN), which integrates content-based deep learning modelswith a collaborative scheme that is able to robustly model and estimateuncertainty. Finally, we present online and offline results after incorporatingDNN into a real world content recommendation system that serves billions ofrecommendations per day, and show the benefit of using DDN in practice.

Deep density networks and uncertainty in recommender systems