Conference
Open access
2026
Comparative Analysis of Neural Network Architectures for Digital Predistortion in Power Amplifier Linearization
Simulation results show that while CNNs offer a favorable trade-off between linearization performance and model complexity, GRU and LSTM architectures achieve the best overall NMSE and ACPR improvements, albeit with a higher number of parameters.
Hafsa Laakouri, M. Ouadefli, A. Tribak et al.
· EPJ Web of Conferences · 0 citations