A Comparative Analysis of MLP and Kolmogorov-Arnold Networks (KAN) for Faster-than-Nyquist (FTN) Signaling Detection

2026-08-03

AI Summary

This work addresses the high complexity and poor scalability of conventional sequence detectors in Faster-than-Nyquist (FTN) signaling by introducing, for the first time, Kolmogorov–Arnold Networks (KANs) for FTN BPSK signal detection. Leveraging a large-scale Monte Carlo dataset comprising nearly four million samples, the study employs end-to-end learning under AWGN channel conditions with a time packing factor of 0.8 and SNR ranging from 7 to 10 dB. Experimental results demonstrate that at 10 dB, the KAN-based detector achieves a bit error rate (BER) as low as \(7 \times 10^{-6}\), outperforming a multilayer perceptron (MLP) under identical conditions by a factor of 18.6 while utilizing only one-eighth of the MLP’s parameters, thereby significantly enhancing both detection accuracy and parameter efficiency.

Abstract

Faster-than-Nyquist signaling improves spectral ef- ficiency by deliberately introducing inter-symbol interference. Classical sequence detectors such as BCJR can approach optimal performance, but their computational cost grows rapidly with channel memory. This paper investigates data-driven FTN BPSK detection under AWGN through a direct comparison between multilayer perceptrons and Kolmogorov Arnold Networks. A large-scale Monte Carlo dataset containing nearly four million labeled windows is generated for a time-packing factor of zero point eight and signal-to-noise ratio values from seven to ten decibels. The best MLP obtained from width sweeping uses hidden width thirty two, whereas the selected KAN uses hidden width four with spline grid size five. At ten decibels, the MLP produces a bit error rate of one point three times ten to the minus four, while the KAN reaches seven times ten to the minus six. This corresponds to an eighteen point six times lower bit error rate while using only one eighth of the MLP hidden width. The results show that KAN provides a more effective and more parameter-efficient neural decision model than the MLP baseline for FTN BPSK detection.

Problem

• Faster-than-Nyquist signaling
• inter-symbol interference
• neural detection
• bit error rate
• parameter efficiency

Innovation

• Kolmogorov-Arnold Networks
• Faster-than-Nyquist signaling
• neural detection
• parameter efficiency
• bit error rate