Answers are grounded in this paper and cite their sources.
This analysis reveals strong performance variations of six spectral-domain activation functions, highlighting trade-offs in efficiency and signal quality.
Spectral Convolutional Neural Networks (SpCNNs) represent a critical domain in signal processing and machine learning, where the integration of activation functions (AFs) presents significant computational and theoretical challenges. This study systematically evaluates six spectral-domain AFs, employing a comprehensive methodology that assesses their performance across multiple critical metrics including signal quality, computational efficiency, and spectral domain characteristics. Using the MNIST dataset and a high-performance computational infrastructure, we conducted a rigorous analysis of AFs including ACReLU, SReLU, Split-tanh, Split-LReLU, PhaseReLU, and ModReLU. Our findings reveal substantial variations in signal processing capabilities, with novel AFs demonstrating marked improvements in signal quality metrics. Notably, Split-tanh and Split-LReLU exhibited significant noise reduction, achieving Signal-to-Noise Ratio (SNR) and Peak Signal-to-Noise Ratio (PSNR) values approaching 0 dB and 9.47 dB, respectively, compared to traditional AFs. The research provides critical insights into the trade-offs between computational efficiency and signal transformation capabilities, highlighting the potential of advanced spectral-domain AFs in improving neural network performance across complex signal processing tasks.
No takes yet. Share an insight, caveat, or question.
Alshareef et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: