Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling
Study shows nested-window Bi-LSTM architectures do not improve faster-than-Nyquist detection; pre-whitening plus BCJR distillation cuts bit error rates.
Across roughly 260 controlled trainings, processing nested intersymbol-interference windows in separate recurrent branches never significantly beat a plain Bi-LSTM at matched parameter budgets. The authors attribute the limitation to the observation model rather than architecture, and instead pre-whiten inputs and distill BCJR soft posteriors into the network. With 3.4% more parameters, the method reaches 1.05x the BCJR bit error rate at compression factor 0.8 and 1.89x at 0.7, improving to 1.47x with a wider whitened window.
- Multi-window Bi-LSTM showed no significant BER improvement across roughly 260 trainings
- Pre-whitening restores conditional independence broken by colored matched-filter noise
- BCJR posterior distillation cuts BER by 23.7% at compression factor 0.8
From the original article
1 min read at arxiv.orgRecurrent detectors such as bidirectional long short-term memory (Bi-LSTM) networks are low-complexity alternatives to the optimal Bahl-Cocke-Jelinek-Raviv (BCJR) detector for faster-than-Nyquist (FTN) signaling.
By Nurettin Safak · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.