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

The sixth-generation (6G) mobile networks are expected to feature theubiquitous deployment of machine learning and AI algorithms at the networkedge. With rapid advancements in edge AI, the time has come to realizeintelligence downloading onto edge devices (e.g., smartphones and sensors). Tomaterialize this version, we propose a novel technology in this article, calledin-situ model downloading, that aims to achieve transparent and real-timereplacement of on-device AI models by downloading from an AI library in thenetwork. Its distinctive feature is the adaptation of downloading totime-varying situations (e.g., application, location, and time), devices'heterogeneous storage-and-computing capacities, and channel states. A keycomponent of the presented framework is a set of techniques that dynamicallycompress a downloaded model at the depth-level, parameter-level, or bit-levelto support adaptive model downloading. We further propose a virtualized 6Gnetwork architecture customized for deploying in-situ model downloading withthe key feature of a three-tier (edge, local, and central) AI library.Furthermore, experiments are conducted to quantify 6G connectivity requirementsand research opportunities pertaining to the proposed technology are discussed.

In-situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks