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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep-learning (DL) has emerged as a powerful machine-learning technique forseveral classic problems encountered in generic wireless communications.Specifically, random Fourier Features (RFF) based deep-learning has emerged asan attractive solution for several machine-learning problems; yet there is alacuna of rigorous results to justify the viability of RFF based DL-algorithmsin general. To address this gap, we attempt to analytically quantify theviability of RFF based DL. Precisely, in this paper, analytical proofs arepresented demonstrating that RFF based DL architectures have lowerapproximation-error and probability of misclassification as compared toclassical DL architectures. In addition, a new distribution-dependent RFF isproposed to facilitate DL architectures with low training-complexity. Throughcomputer simulations, the practical application of the presented analyticalresults and the proposed distribution-dependent RFF, are depicted for variousmachine-learning problems encountered in next-generation communication systemssuch as: a) line of sight (LOS)/non-line of sight (NLOS) classification, and b)message-passing based detection of low-density parity check codes (LDPC) codesover nonlinear visible light communication (VLC) channels. Especially in thelow training-data regime, the presented simulations show that significantperformance gains are achieved when utilizing RFF maps of observations. Lastly,in all the presented simulations, it is observed that the proposeddistribution-dependent RFFs significantly outperform RFFs, which make themuseful for potential machine-learning/DL based applications in the context ofnext-generation communication systems.

Random Fourier Feature Based Deep Learning for Wireless Communications