In the last decades it often has been shown that Multilayer Perceptrons (MLPs) are powerful function approximators. They were successfully applied to a lot of different classification problems. However, originally they only deal with real valued numbers. Since PolSAR data is a complex valued signal this paper propose the usage of Complex Valued Neural Networks (CVNNs), which are an extension of...

Routing is one of the basic parts of a message passing multiprocessor system. The routing procedure has a great impact on the efficiency of a system. Neural algorithms that are currently in use for computer networks require a large number of neurons. If a specific topology of a multiprocessor network is considered, the number of neurons can be reduced. In this paper a new recurrent neural ne...

This paper focuses on investigating the finite-time projective synchronization of Caputo type fractional-order complex-valued neural networks with time delay (FOCVNNTD). Based properties fractional calculus and various inequality techniques, by constructing suitable Lyapunov function designing two new types controllers, i.e., feedback controller adaptive controller, sufficient criteria are deri...

This paper discusses the novel synchronization conditions about unified system of multi-dimension-valued neural networks (USOMDVNN). First all, general model USOMDVNN is successfully set up, mainly on basis multidimensional algebra, Kirchhoff current law, and neuronal property. Then, concise Lyapunov–Krasovskii functional (LKF) switching controllers are constructed for USOMDVNN. Moreover, new i...

We show that the class of two layer neural networks with bounded fan-in is eeciently learn-able in a realistic extension to the Probably Approximately Correct (PAC) learning model. In this model, a joint probability distribution is assumed to exist on the observations and the learner is required to approximate the neural network which minimizes the expected quadratic error. As special cases, th...

Based on direct quaternion method, this paper explores the finite-time adaptive synchronization (FAS) of fractional-order delayed quaternion-valued fuzzy neural networks (FODQVFNNs). Firstly, a useful fractional differential inequality is created, which offers an effective way to investigate FAS. Then two novel control strategies are designed. By means our newly proposed inequality, basic knowl...