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 the design of wireless receivers, DNNs can be combined with traditionalmodel-based receiver algorithms to realize modular hybridmodel-based/data-driven architectures that can account for domain knowledge.Such architectures typically include multiple modules, each carrying out adifferent functionality. Conventionally trained DNN-based modules are known toproduce poorly calibrated, typically overconfident, decisions. This impliesthat an incorrect decision may propagate through the architecture without anyindication of its insufficient accuracy. To address this problem, we present anovel combination of Bayesian learning with hybrid model-based/data-drivenarchitectures for wireless receiver design. The proposed methodology, referredto as modular model-based Bayesian learning, results in better calibratedmodules, improving accuracy and calibration of the overall receiver. Wedemonstrate this approach for the recently proposed DeepSIC MIMO receiver,showing significant improvements with respect to the state-of-the-art learningmethods.

Modular Model-Based Bayesian Learning for Uncertainty-Aware and Reliable Deep MIMO Receivers