Stability and synchronization of octonion-valued neural networks with leakage and mixed delays on time scales
Open Access
- 22 June 2024
- journal article
- research article
- Published by Springer Nature in Computational and Applied Mathematics
- Vol. 43 (5) , 1-26
Abstract
There has been a great deal of interest in the last few years for neural networks (NNs) with values in multidimensional domains. The most popular models are complex-valued neural networks (CVNNs), followed by quaternion-valued neural networks (QVNNs), and, more recently, by Clifford-valued neural networks (ClVNNs). However, also very recently, a different type of NNs were put forward, namely octonion-valued neural networks (OVNNs). OVNNs are defined on the 8D octonion algebra, and they are not a special type of ClVNNs, because Clifford numbers are associative, whereas octonions are not. Moreover, beside the complex and quaternion algebras, the only other normed division algebra over the reals is the algebra of octonions, which makes OVNNs a direct generalization of CVNNs and QVNNs from this point of view, raising interest for applications handling high-dimensional data. On the other hand, systems defined on time scales were proposed as a generalization of both discrete time and continuous time systems, or any type of hybrid combination between the two. Finally, time delays appear as a consequence of implementing NNs in real life circuits. Taking all these into consideration, this paper studies the fundamental properties of exponential stability and exponential synchronization for OVNNs with leakage and mixed delays defined on time scales. In order to avoid the problems raised by the non-associativity of the octonion algebra, the OVNN model is decomposed into a real-valued one. Then, two different Lyapunov-type functionals are defined and the particularities of time scale calculus are used in order to deduce sufficient conditions expressed as scalar and linear matrix inequalities (LMIs) for the exponential stability of the proposed models, based on Halanay-type inequalities suitable for time scale systems. Afterwards, a state feedback controller is used to deduce sufficient criteria given as scalar inequalities and LMIs for the exponential synchronization of the same type of models. The generality of the model, given by the definition on the algebra of octonions, the use of different types of delays, and the definition on time scales represent an important advantage. Also, for less general models, it is possible to particularize the obtained results. With the aim to demonstrate each of the paper’s four theorems, four numerical examples are provided.Keywords
Funding Information
- UEFISCDI (PN-III-P1-1.1-PD-2021-0345)
This publication has 42 references indexed in Scilit:
- Weyl almost periodic solutions of octonion-valued high-order fuzzy neural networks with delaysComputational and Applied Mathematics, 2023
- A neutral fractional Halanay inequality and application to a Cohen–Grossberg neural network systemMathematical Methods in the Applied Sciences, 2021
- Halanay Inequality on Time Scales with Unbounded Coefficients and Its ApplicationsIndian Journal of Pure and Applied Mathematics, 2020
- Stability, Periodicity and Boundedness in Functional Dynamical Systems on Time Scales2020
- Octonion-Valued Neural Networks2016
- Stability Theory for Dynamic Equations on Time Scales2016
- Octonion massive electrodynamicsGeneral Relativity and Gravitation, 2013
- Hyperbolic Octonion Formulation of Gravitational Field EquationsInternational Journal of Theoretical Physics, 2012
- Dynamic Equations on Time Scales2001
- Analysis on Measure Chains — A Unified Approach to Continuous and Discrete CalculusResults in Mathematics, 1990