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

Deep learning has seen a rapid adoption in a variety of wirelesscommunications applications, including at the physical layer. While it hasdelivered impressive performance in tasks such as channel equalization andreceive processing/symbol detection, it leaves much to be desired when it comesto explaining this superior performance. In this work, we investigate thespecific task of channel equalization by applying a popular learning-basedtechnique known as Reservoir Computing (RC), which has shown superiorperformance compared to conventional methods and other learning-basedapproaches. Specifically, we apply the echo state network (ESN) as a channelequalizer and provide a first principles-based signal processing understandingof its operation. With this groundwork, we incorporate the available domainknowledge in the form of the statistics of the wireless channel directly intothe weights of the ESN model. This paves the way for optimized initializationof the ESN model weights, which are traditionally untrained and randomlyinitialized. Finally, we show the improvement in receive processing/symboldetection performance with this optimized initialization through simulations.This is a first step towards explainable machine learning (XML) and assigningpractical model interpretability that can be utilized together with theavailable domain knowledge to improve performance and enhance detectionreliability.

Towards Explainable Machine Learning: The Effectiveness of Reservoir Computing in Wireless Receive Processing