A low-complexity complex-valued activation function for fast and accurate spectral domain convolutional neural network

• Main Authors: Rizvi, S. M., Ab. Rahman, A. A. H., Hani, M. K., Ayat, S. O.
• Format: Article
• Language: English
• Published: Institute of Advanced Engineering and Science 2021
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/id/eprint/95359/1/ShahriyarMasudRizvi2021_ALowComplexityComplex.pdf; http://eprints.utm.my/id/eprint/95359/; http://dx.doi.org/10.11591/ijeei.v9i1.2737
• Institution: Universiti Teknologi Malaysia

Conventional Convolutional Neural Networks (CNNs), which are realized in spatial domain, exhibit high computational complexity. This results in high resource utilization and memory usage and makes them unsuitable for implementation in resource and energy-constrained embedded systems. A promising app...