Traditional neural networks used gradient descent methods to train the network structure, which cannot handle complex optimization problems. We proposed an improved grey wolf optimizer (SGWO) to explore a better network structure. GWO was improved by using circle population initialization, information interaction mechanism and adaptive position update to enhance the search performance of the algorithm. SGWO was applied to optimize Elman network structure, and a new prediction method (SGWO-Elman) was proposed. The convergence of SGWO was analyzed by mathematical theory, and the optimization ability of SGWO and the prediction performance of SGWO-Elman were examined using comparative experiments. The results show: (1) the global convergence probability of SGWO was 1, and its process was a finite homogeneous Markov chain with an absorption state; (2) SGWO not only has better optimization performance when solving complex functions of different dimensions, but also when applied to Elman for parameter optimization, SGWO can significantly optimize the network structure and SGWO-Elman has accurate prediction performance.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10328355 | PMC |
| http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0288071 | PLOS |
Publication Analysis
Top Keywords
Similar Publications
Weighted Echo State Graph Neural Networks Based on Robust and Epitaxial Film Memristors.
Adv Sci (Weinh)
January 2025
College of Physics Science & Technology, School of Life Sciences, Institute of Life Science and Green Development, Key Laboratory of Brain-Like Neuromorphic Devices and Systems of Hebei Province, Hebei University, Baoding, 071002, China.
Hardware system customized toward the demands of graph neural network learning would promote efficiency and strong temporal processing for graph-structured data. However, most amorphous/polycrystalline oxides-based memristors commonly have unstable conductance regulation due to random growth of conductive filaments. And graph neural networks based on robust and epitaxial film memristors can especially improve energy efficiency due to their high endurance and ultra-low power consumption.
View Article and Find Full Text PDFHigh-Throughput Formation of Pre-Vascularized hiPSC-Derived Hepatobiliary Organoids on a Chip via Nonparenchymal Cell Grafting.
Adv Sci (Weinh)
January 2025
Tissue Engineering and Organ Manufacturing (TEOM) Lab, Department of Biomedical Engineering, Wuhan University TaiKang Medical School (School of Basic Medical Sciences), Wuhan, 430071, China.
Liver organoids have been increasingly adopted as a critical in vitro model to study liver development and diseases. However, the pre-vascularization of liver organoids without affecting liver parenchymal specification remains a long-lasting challenge, which is essential for their application in regenerative medicine. Here, the large-scale formation of pre-vascularized human hepatobiliary organoids (vhHBOs) is presented without affecting liver epithelial specification via a novel strategy, namely nonparenchymal cell grafting (NCG).
View Article and Find Full Text PDFCopy Number Variation in Asthma: An Integrative Review.
Clin Rev Allergy Immunol
January 2025
Postgraduate Program in Biochemistry, Federal University of Espírito Santo (UFES), Vitória, Espírito Santo, Brazil.
Asthma is a complex disease with varied clinical manifestations resulting from the interaction between environmental and genetic factors. While chronic airway inflammation and hyperresponsiveness are central features, the etiology of asthma is multifaceted, leading to a diversity of phenotypes and endotypes. Although most research into the genetics of asthma focused on the analysis of single nucleotide polymorphisms (SNPs), studies highlight the importance of structural variations, such as copy number variations (CNVs), in the inheritance of complex characteristics, but their role has not yet been fully elucidated in asthma.
View Article and Find Full Text PDFUnifying topological structure and self-attention mechanism for node classification in directed networks.
Sci Rep
January 2025
College of Computer and Information Engineering, Nanjing Tech University, Nanjing, 211800, China.
Graph data is essential for modeling complex relationships among entities. Graph Neural Networks (GNNs) have demonstrated effectiveness in processing low-order undirected graph data; however, in complex directed graphs, relationships between nodes extend beyond first-order connections and encompass higher-order relationships. Additionally, the asymmetry introduced by edge directionality further complicates node interactions, presenting greater challenges for extracting node information.
View Article and Find Full Text PDFHierarchically aligned heterogeneous core-sheath hydrogels.
Nat Commun
January 2025
Institute of Innovative Materials, Department of Chemistry, College of Science, Southern University of Science and Technology, Shenzhen, China.
Natural materials with highly oriented heterogeneous structures are often lightweight but strong, stiff but tough and durable. Such an integration of diverse incompatible mechanical properties is highly desired for man-made materials, especially weak hydrogels which are lack of high-precision structural design. Herein, we demonstrate the fabrication of hierarchically aligned heterogeneous hydrogels consisting of a compactly crosslinked sheath and an aligned porous core with alignments of nanofibrils at multi-scales by a sequential self-assembly assisted salting out method.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!