Multistability of Fractional-Order Recurrent Neural Networks With Discontinuous and Nonmonotonic Activation Functions

Abstract

The coexistence of multiple stable equilibria in recurrent neural networks is an important dynamic characteristic for associative memory and other applications. In this paper, the existence and local Mittag-Leffler stability of multiple equilibria are investigated for a class of fractional-order recurrent neural networks with discontinuous and nonmonotonic activation functions. By using Brouwer s fixed point theory, several conditions are established to ensure the existence of 5 n equilibria, in which all the components of 4 n equilibria are located in the continuous intervals of the activation functions. and some of the components of 5 n − 4 n equilibria are located at some discontinuous points of the activation functions. The introduction of discontinuous activation functions makes the neural networks have more equilibria than those with continuous activation functions. Furthermore, some criteria are proposed to ensure local Mittag-Leffler stability of 3 n equilibria. The introduction of nonmonotonic activation functions makes the neural networks have more stable equilibria than those with monotonic activation functions. Two examples are given to illustrate the effectiveness of the results. INDEX TERMS Fractional-order recurrent neural network, discontinuous and nonmonotonic activation function, equilibrium point, local Mittag-Leffler stability.

An automatic approach to fetal magnetic resonance image segmentation using 2D U-Net Architecture

“…They take an input signal in a neural network and transforms it into a non-linear output [29]. The simplest ones are linear, but because they do not apply radical transformations, they cannot be successfully used for complex problems [30]. The more commonly used activation functions in medical image segmentation are non-linear because they can work with more complicated structures in the data.…”

“…Once the activation function is applied to each neuron, the model can synthesize whether the neuron is valuable to the model to make accurate predictions [29]. If activation functions were removed, the neuronal layers would not be regularized, and the weights between the nodes would not hold appropriate values [30]. Without activation functions, the algorithms risk failing to converge or increasing the training times.…”

Divergence Measure on a Modified Sprott-C System

“…Lorenz discovered the first chaotic attractor in the 1960s [2], Chaos as an important branch of nonlinear system theory, has been developing rapidly and gradually become a hot research topic in the field of modern natural science. In addition, chaos has obtained huge and far-reaching achievements in different research areas, such as stability and bifurcation analysis [3]- [7], coexistence attractor and hidden attractor [8]- [13], chaos control and chaos synchronization [14]- [17], dynamic behavior analysis of memristors, neural network [18]- [22], and so on. After understanding the general laws of chaos, the research of chaos began to develop into the application field [23]- [28].…”

Global Mittag-Leffler Synchronization of Fractional-Order Neural Networks With Time-Varying Delay via Hybrid Sliding Mode Control

“…In [9], fractional-order chaotic systems with completely unknown dynamics and structure are proposed to study power systems. Recently, based on the unique advantages of fractional calculus, fractional-order neural networks (FNNs), as the popular and important kind of networks, are attracted increasing con-cerns [10], [11], [12], [13], [14], [15]. Among these studies, stability and synchronization of FNNs are always major topics and many sufficient conditions have been proposed for the FNNs with or without time delay.…”

“…Asymptotic and finite-time cluster synchronization criteria of coupled FNNs with time delay are proposed in [14]. In [15], the existence and local Mittag-Leffler (ML) stability of multiple equilibria are studied for a class of FNNs with discontinuous and nonmonotonic activation functions.…”