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 neural network (DNN)-assisted channel coding designs, such aslow-complexity neural decoders for existing codes, or end-to-endneural-network-based auto-encoder designs are gaining interest recently due totheir improved performance and flexibility; particularly for communicationscenarios in which high-performing structured code designs do not exist.Communication in the presence of feedback is one such communication scenario,and practical code design for feedback channels has remained an open challengein coding theory for many decades. Recently, DNN-based designs have shownimpressive results in exploiting feedback. In particular, generalized blockattention feedback (GBAF) codes, which utilizes the popular transformerarchitecture, achieved significant improvement in terms of the block error rate(BLER) performance. However, previous works have focused mainly on passivefeedback, where the transmitter observes a noisy version of the signal at thereceiver. In this work, we show that GBAF codes can also be used for channelswith active feedback. We implement a pair of transformer architectures, at thetransmitter and the receiver, which interact with each other sequentially, andachieve a new state-of-the-art BLER performance, especially in the low SNRregime.

Feedback is Good, Active Feedback is Better: Block Attention Active Feedback Codes