Recent reports show that projection neural networks with a low-dimensional state space can enhance computation speed obviously. This paper proposes two projection neural networks with reduced model dimension and complexity (RDPNNs) for solving nonlinear programming (NP) problems. Compared with existing projection neural networks for solving NP, the proposed two RDPNNs have a low-dimensional state space and low model complexity. Under the condition that the Hessian matrix of the associated Lagrangian function is positive semi-definite and positive definite at each Karush-Kuhn-Tucker point, the proposed two RDPNNs are proven to be globally stable in the sense of Lyapunov and converge globally to a point satisfying the reduced optimality condition of NP. Therefore, the proposed two RDPNNs are theoretically guaranteed to solve convex NP problems and a class of nonconvex NP problems. Computed results show that the proposed two RDPNNs have a faster computation speed than the existing projection neural networks for solving NP problems.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNNLS.2019.2927639 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Predicting home delivery and identifying its determinants among women aged 15-49 years in sub-Saharan African countries using a Demographic and Health Surveys 2016-2023: a machine learning algorithm.
BMC Public Health
January 2025
Department of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia.
Background: Birth-related mortality is significantly increased by home births without skilled medical assistance during delivery, presenting a major risk to the public's health. The objective of this study is to predict home delivery and identify the determinants using machine learning algorithm in sub-Saharan African.
Methods: This study used design science approaches.
Ventral hippocampus to nucleus accumbens shell circuit regulates approach decisions during motivational conflict.
PLoS Biol
January 2025
Department of Cell and Systems Biology, University of Toronto, Toronto, Canada.
Successful resolution of approach-avoidance conflict (AAC) is fundamentally important for survival, and its dysregulation is a hallmark of many neuropsychiatric disorders, and yet the underlying neural circuit mechanisms are not well elucidated. Converging human and animal research has implicated the anterior/ventral hippocampus (vHPC) as a key node in arbitrating AAC in a region-specific manner. In this study, we sought to target the vHPC CA1 projection pathway to the nucleus accumbens (NAc) to delineate its contribution to AAC decision-making, particularly in the arbitration of learned reward and punishment signals, as well as innate signals.
View Article and Find Full Text PDFDiscriminating neural ensemble patterns through dendritic computations in randomly connected feedforward networks.
Elife
January 2025
National Centre for Biological Sciences, Tata Institute of Fundamental Research, Bangalore, India.
Co-active or temporally ordered neural ensembles are a signature of salient sensory, motor, and cognitive events. Local convergence of such patterned activity as synaptic clusters on dendrites could help single neurons harness the potential of dendritic nonlinearities to decode neural activity patterns. We combined theory and simulations to assess the likelihood of whether projections from neural ensembles could converge onto synaptic clusters even in networks with random connectivity.
View Article and Find Full Text PDFOptimized genetic tools for neuroanatomical and functional mapping of the Aedes aegypti olfactory system.
G3 (Bethesda)
January 2025
W. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Malaria Research Institute, Johns Hopkins Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, USA.
The mosquito Aedes aegypti is an emerging model insect for invertebrate neurobiology. We detail the application of a dual transgenesis marker system that reports the nature of transgene integration with circular donor template for CRISPR-Cas9-mediated homology-directed repair at target mosquito chemoreceptor genes. Employing this approach, we demonstrate the establishment of cell-type-specific T2A-QF2 driver lines for the A.
View Article and Find Full Text PDFForecasting Stock Market Indices Using Integration of Encoder, Decoder, and Attention Mechanism.
Entropy (Basel)
January 2025
Faculty of Mathematics and Statistics, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam.
Accurate forecasting of stock market indices is crucial for investors, financial analysts, and policymakers. The integration of encoder and decoder architectures, coupled with an attention mechanism, has emerged as a powerful approach to enhance prediction accuracy. This paper presents a novel framework that leverages these components to capture complex temporal dependencies and patterns within stock price data.
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!