Academic Journal

Fixed-time synchronization of competitive neural networks with multiple time-scale

التفاصيل البيبلوغرافية
العنوان: Fixed-time synchronization of competitive neural networks with multiple time-scale
المؤلفون: Yang, Wu, Wang, Yan-Wu, Morarescu, Irinel-Constantin, Liu, Xiao-Kang, Huang, Yuehua
المساهمون: Huazhong University of Science and Technology Wuhan (HUST), Centre de Recherche en Automatique de Nancy (CRAN), Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), China Three Gorges University, ANR-18-CE40-0010,HANDY,Systèmes Dynamiques Hybrides et en Réseau(2018)
المصدر: ISSN: 2162-237X ; IEEE Transactions on Neural Networks and Learning Systems ; https://hal.science/hal-03455236 ; IEEE Transactions on Neural Networks and Learning Systems, 2021, pp.Early Access. ⟨10.1109/TNNLS.2021.3052868⟩.
بيانات النشر: HAL CCSD
IEEE
سنة النشر: 2021
المجموعة: Université de Lorraine: HAL
مصطلحات موضوعية: [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering
الوصف: International audience ; In this brief we investigate the fixed-time synchronization of competitive neural networks with multiple timescales. These neural networks play an important role in visual processing, pattern recognition, neural computing, etc. Our main contribution is the design of a novel synchronizing controller which does not depend on the ratio between the fast and slow time scales. This feature makes the controller easy to implement since it is designed through well-posed algebraic conditions (i.e. even when the ratio between the time scales goes to 0 the controller gain is well defined and does not go to infinity). Last but not least, the closed-loop dynamics is characterized by a high convergence speed with a settling time which is upper-bounded and the bound is independent of the initial conditions. A numerical simulation illustrates our results and emphasizes their effectiveness. Index Terms-Competitive neural network, multiple timescale feature, fixed-time synchronization, continuous control method.
نوع الوثيقة: article in journal/newspaper
اللغة: English
Relation: hal-03455236; https://hal.science/hal-03455236; https://hal.science/hal-03455236/document; https://hal.science/hal-03455236/file/TNNLS-2020.pdf
DOI: 10.1109/TNNLS.2021.3052868
الاتاحة: https://hal.science/hal-03455236
https://hal.science/hal-03455236/document
https://hal.science/hal-03455236/file/TNNLS-2020.pdf
https://doi.org/10.1109/TNNLS.2021.3052868
Rights: info:eu-repo/semantics/OpenAccess
رقم الانضمام: edsbas.A05581D0
قاعدة البيانات: BASE