Fractional-order neural networks play a vital role in modeling the information processing of neuronal interactions. It is still an open and necessary topic for fractional-order neural networks to investigate their global stability. This paper proposes some simplified linear matrix inequality (LMI) stability conditions for fractional-order linear and nonlinear systems. Then, the global stability analysis of fractional-order neural networks employs the results from the obtained LMI conditions. In the LMI form, the obtained results include the existence and uniqueness of equilibrium point and its global stability, which simplify and extend some previous work on the stability analysis of the fractional-order neural networks. Moreover, a generalized projective synchronization method between such neural systems is given, along with its corresponding LMI condition. Finally, two numerical examples are provided to illustrate the effectiveness of the established LMI conditions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNNLS.2016.2574842 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
H control for fractional order neural networks with uncertainties subject to deception attacks via Improved memory-event-triggered scheme and Its application.
Neural Netw
December 2024
Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen 518055, PR China. Electronic address:
The article discusses an improved memory-event-triggered strategy for H control class of fractional-order neural networks (FONNs) with uncertainties, which are vulnerable to deception attacks. The system under consideration is simultaneously influenced by external disturbances, network-induced time delays, uncertainties, and deception attacks. The suggested enhanced memory event-triggered framework enhances communications security measures and conserves network bandwidth compared to standard control strategies.
View Article and Find Full Text PDFGeneralized fractional optimization-based explainable lightweight CNN model for malaria disease classification.
Comput Biol Med
February 2025
Future Technology Research Center, National Yunlin University of Science and Technology, 123 University Road, Section 3, Douliou, Yunlin, 64002, Taiwan. Electronic address:
Over the past few decades, machine learning and deep learning (DL) have incredibly influenced a broader range of scientific disciplines. DL-based strategies have displayed superior performance in image processing compared to conventional standard methods, especially in healthcare settings. Among the biggest threats to global public health is the fast spread of malaria.
View Article and Find Full Text PDFEffects of high-order interactions on synchronization of a fractional-order neural system.
Cogn Neurodyn
August 2024
Clinical Engineering Research and Implementation Center (ERKAM), Erciyes University, 38030 Kayseri, Turkey.
Unlabelled: In this study, effects of high-order interactions on synchronization of the fractional-order Hindmarsh-Rose neuron models have been examined deeply. Three different network situations in which first-order coupling, high-order couplings and first-plus second-order couplings included in the neuron models, have been considered, respectively. In order to find the optimal values of the first- and high-order coupling parameters by minimizing the cost function resulted from pairwise and triple interactions, the particle swarm optimization algorithm is employed.
View Article and Find Full Text PDFCluster synchronization of fractional-order two-layer networks and application in image encryption/decryption.
Neural Netw
December 2024
College of Mathematics and System Sciences, Xinjiang University, Urumqi 830017, China; Xinjiang Key Laboratory of Applied Mathematics, Urumqi, 830017, China. Electronic address:
In this paper, a type of fractional-order two-layer network model is constructed, wherein each layer in the network exhibits distinct topology. Subsequently, the cluster synchronization problem of fractional-order two-layer networks is investigated through a two-step approach. The initial step involves the implementation of finite-time cluster synchronization in the first layer by utilizing a fractional-order finite-time convergence lemma.
View Article and Find Full Text PDFNeural networks with optimized single-neuron adaptation uncover biologically plausible regularization.
PLoS Comput Biol
December 2024
Mila - Quebec Artificial Intelligence Institute, Montréal, Canada.
Neurons in the brain have rich and adaptive input-output properties. Features such as heterogeneous f-I curves and spike frequency adaptation are known to place single neurons in optimal coding regimes when facing changing stimuli. Yet, it is still unclear how brain circuits exploit single-neuron flexibility, and how network-level requirements may have shaped such cellular function.
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!