Non-linear Equalization in 112 Gb/s PONs Using Kolmogorov-Arnold Networks

2024/11/29 by Fischer, Rodrigo, Patrick Matalla, Sebastian Randel +4
Engineering · #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Optical Network Technologies #Photonic and Optical Devices #Semiconductor Lasers and Optical Devices #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2411.19631

openalex publication_date 2024/11/29 · openalex created_date 2024/12/05 · openalex updated_date 2026/07/30

Abstract

We investigate Kolmogorov-Arnold networks (KANs) for non-linear equalization of 112 Gb/s PAM4 passive optical networks (PONs). Using pruning and extensive hyperparameter search, we outperform linear equalizers and convolutional neural networks at low computational complexity.

Related

• Fully-blind Neural Network Based Equalization for Severe Nonlinear Distortions in 112 Gbit/s Passive Optical Networks
• Advanced Equalization in 112 Gb/s Upstream PON Using a Novel Fourier Convolution-based Network
• Real-Time FPGA Demonstrator of ANN-Based Equalization for Optical Communications
• Experimental Study of Deep Neural Network Equalizers Performance in Optical Links
• Neural Network Equalizers and Successive Interference Cancellation for Bandlimited Channels with a Nonlinearity