Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Artificial neural networks (ANNs) have become a popular tool in digital signal processing (DSP). Among the widespread ANN architectures, complex-valued neural networks (CVNNs) have been extensively studied in image processing and telecommunications. Unlike their real-valued counterparts, CVNNs can handle signals directly in the complex domain. Due to this capability, CVNNs usually exhibit higher accuracy and improved convergence compared to real-valued neural networks (RVNNs). Despite their improved performance in several applications, CVNNs still lag behind RVNNs in terms of learning techniques and heuristics. In this context, we propose adaptive learning rate approaches for CVNNs, extending the well-known adaptive gradient (AdaGrad), root-mean-square propagation (RMSProp), AdaMax, AMSGrad, softplus AMSGrad (SAMSGrad), Nesterov-accelerated adaptive moment estimation (Nadam), and DiffGrad to the complex domain. Computational complexities of the proposed optimizers are analyzed for CVNN architectures. Results are compared in terms of mean-squared-error convergence.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNNLS.2025.3596513 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Maximizing theoretical and practical storage capacity in single-layer feedforward neural networks.
Front Comput Neurosci
August 2025
Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States.
Artificial neural networks are limited in the number of patterns that they can store and accurately recall, with capacity constraints arising from factors such as network size, architectural structure, pattern sparsity, and pattern dissimilarity. Exceeding these limits leads to recall errors, eventually leading to catastrophic forgetting, which is a major challenge in continual learning. In this study, we characterize the theoretical maximum memory capacity of single-layer feedforward networks as a function of these parameters.
View Article and Find Full Text PDFHigh-resolution imaging system for integration into intelligent noncontact total body scanner.
J Biomed Opt
September 2025
Leibniz University Hannover, Hannover Centre for Optical Technologies, Hannover, Germany.
Significance: Melanoma's rising incidence demands automatable high-throughput approaches for early detection such as total body scanners, integrated with computer-aided diagnosis. High-quality input data is necessary to improve diagnostic accuracy and reliability.
Aim: This work aims to develop a high-resolution optical skin imaging module and the software for acquiring and processing raw image data into high-resolution dermoscopic images using a focus stacking approach.
Phasor and neural network approaches for rapid fluorophore fraction analysis in temporal-spectral multiplexed data.
J Biomed Opt
September 2025
Fraunhofer Institute for Microelectronic Circuits and Systems IMS, Duisburg, Germany.
Significance: The spatial and temporal distribution of fluorophore fractions in biological and environmental systems contains valuable information about the interactions and dynamics of these systems. To access this information, fluorophore fractions are commonly determined by means of their fluorescence emission spectrum (ES) or lifetime (LT). Combining both dimensions in temporal-spectral multiplexed data enables more accurate fraction determination while requiring advanced and fast analysis methods to handle the increased data complexity and size.
View Article and Find Full Text PDFHybrid two-stage CNN for detection and staging of periodontitis on panoramic radiographs.
J Oral Biol Craniofac Res
August 2025
Neura Integrasi Solusi, Jl. Kebun Raya No. 73, Rejowinangun, Kotagede, Yogyakarta, 55171, Indonesia.
Background: Periodontal disease is an inflammatory condition causing chronic damage to the tooth-supporting connective tissues, leading to tooth loss in adults. Diagnosing periodontitis requires clinical and radiographic examinations, with panoramic radiographs crucial in identifying and assessing its severity and staging. Convolutional Neural Networks (CNNs), a deep learning method for visual data analysis, and Dense Convolutional Networks (DenseNet), which utilize direct feed-forward connections between layers, enable high-performance computer vision tasks with reduced computational demands.
View Article and Find Full Text PDFDeepRNAac4C: a hybrid deep learning framework for RNA N4-acetylcytidine site prediction.
Front Genet
August 2025
Hunan Provincial Key Laboratory of Finance and Economics Big Data Science and Technology, Hunan University of Finance and Economics, Changsha, China.
RNA N4-acetylcytidine (ac4C) is a crucial chemical modification involved in various biological processes, influencing RNA properties and functions. Accurate prediction of RNA ac4C sites is essential for understanding the roles of RNA molecules in gene expression and cellular regulation. While existing methods have made progress in ac4C site prediction, they still struggle with limited accuracy and generalization.
View Article and Find Full Text PDF