In this paper, we consider a class of neural networks with mixed delays and impulsive interferences. Firstly, a sufficient condition is given to ensure the existence and uniqueness of the equilibrium point of the proposed neural networks by employing the contraction mapping theorem. Secondly, we discuss the issue of the exponential stability in mean-square of the equilibrium point by a non-fragilely delayed output coupling feedback which involves stochastically occurring gain oscillations. The designed feedback input can be tolerant of limited stochastic fluctuations of control gains and be robust against potential errors caused by factors like round-off. By combining methods of Lyapunov-Krasovskii functional and free-weighting matrix, a delay-dependent output coupling feedback with stochastically occurring uncertainties is designed and linear-matrix-inequalities(LMIs)-based sufficient conditions for the exponential stabilization in mean square are derived. Finally, three numerical examples are presented to illustrate the feasibility of theoretical results with a benchmark real-world problem.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2022.07.006 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Physiology-informed regularisation enables training of universal differential equation systems for biological applications.
PLoS Comput Biol
January 2025
Deparment of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands.
Systems biology tackles the challenge of understanding the high complexity in the internal regulation of homeostasis in the human body through mathematical modelling. These models can aid in the discovery of disease mechanisms and potential drug targets. However, on one hand the development and validation of knowledge-based mechanistic models is time-consuming and does not scale well with increasing features in medical data.
View Article and Find Full Text PDFEvaluating Machine Learning and Deep Learning models for predicting Wind Turbine power output from environmental factors.
PLoS One
January 2025
Renewable Energy Science and Engineering Department, Faculty of Postgraduate Studies for Advanced Sciences (PSAS), Beni-Suef University, Beni-Suef, Egypt.
This study presents a comprehensive comparative analysis of Machine Learning (ML) and Deep Learning (DL) models for predicting Wind Turbine (WT) power output based on environmental variables such as temperature, humidity, wind speed, and wind direction. Along with Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN), the following ML models were looked at: Linear Regression (LR), Support Vector Regressor (SVR), Random Forest (RF), Extra Trees (ET), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). Using a dataset of 40,000 observations, the models were assessed based on R-squared, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE).
View Article and Find Full Text PDFThe tumour histopathology "glossary" for AI developers.
PLoS Comput Biol
January 2025
Centre for Evolution and Cancer, Institute of Cancer Research, London, United Kingdom.
The applications of artificial intelligence (AI) and deep learning (DL) are leading to significant advances in cancer research, particularly in analysing histopathology images for prognostic and treatment-predictive insights. However, effective translation of these computational methods requires computational researchers to have at least a basic understanding of histopathology. In this work, we aim to bridge that gap by introducing essential histopathology concepts to support AI developers in their research.
View Article and Find Full Text PDFMEGA-GO: Functions prediction of diverse protein sequence length using Multi-scalE Graph Adaptive neural network.
Bioinformatics
January 2025
Guangdong Provincial Key Laboratory IRADS, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai, China.
Motivation: The increasing accessibility of large-scale protein sequences through advanced sequencing technologies has necessitated the development of efficient and accurate methods for predicting protein function. Computational prediction models have emerged as a promising solution to expedite the annotation process. However, despite making significant progress in protein research, graph neural networks face challenges in capturing long-range structural correlations and identifying critical residues in protein graphs.
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!