This paper investigates the coexistence and local stability of multiple equilibrium points for a class of competitive neural networks with sigmoidal activation functions and time-varying delays, in which fractional-or...
详细信息
This paper investigates the coexistence and local stability of multiple equilibrium points for a class of competitive neural networks with sigmoidal activation functions and time-varying delays, in which fractional-order derivative and state-dependent switching are involved at the same time. Some novel criteria are established to ensure that such n-neuron neural networks can have 5m1 center dot 3m2 total equilibrium points and 3m1 center dot 2m2 locally stable equilibrium points with m1+m2 = n, based on the fixed-point theorem, the definition of equilibrium point in the sense of Filippov, the theory of fractional-order differential equation and Lyapunov function method. The investigation implies that the competitive neural networks with switching can possess greater storage capacity than the ones without switching. Moreover, the obtained results include the multistability results of both fractional-order switched Hopfield neural networks and integer-order switched Hopfield neural networks as special cases, thus generalizing and improving some existing works. Finally, four numerical examples are presented to substantiate the effectiveness of the theoretical analysis.(c) 2022 Elsevier Ltd. All rights reserved.
This work concerns the identification of the structure of a genetic network model from measurements of gene product concentrations and synthesis rates. In earlier work, we developed a data preprocessing algorithm that...
详细信息
This work concerns the identification of the structure of a genetic network model from measurements of gene product concentrations and synthesis rates. In earlier work, we developed a data preprocessing algorithm that is able to reject many hypotheses on the network structure by testing certain monotonicity properties for a wide family of network models. Here, we develop a geometric interpretation of the method. Then, for a relevant subclass of genetic network models, we extend our approach to the combined testing of monotonicity and convexity-like properties associated with the network structures. The theoretical aspects and practical performance of the enhanced methods are illustrated by way of numerical results. Copyright (c) 2012 John Wiley & Sons, Ltd.
Abstract This work concerns the identification of the structure of a genetic network model from measurements of gene product concentrations and synthesis rates. In earlier work, for a wide family of network models, we...
详细信息
Abstract This work concerns the identification of the structure of a genetic network model from measurements of gene product concentrations and synthesis rates. In earlier work, for a wide family of network models, we developed a data preprocessing algorithm that is able to reject many hypotheses on the network structure by testing certain monotonicity properties of the models. Here we develop a geometric analysis of the method. Then, for a relevant subclass of genetic network models, we extend our approach to the combined testing of monotonicity and convexity-like properties associated with the network structures. Theoretical achievements as well as performance of the enhanced methods are illustrated by way of numerical results.
In this paper we investigate the use of the multi-layer perceptron (MLP) for system modelling. A new sigmoidalactivation function is introduced and the study is focused at the utilization of this function on a MLP th...
详细信息
In this paper we investigate the use of the multi-layer perceptron (MLP) for system modelling. A new sigmoidalactivation function is introduced and the study is focused at the utilization of this function on a MLP that performs modelling of dynamic, discrete time systems. The role of the activation function in the training process is investigated analytically, and it is proven that the shape of the activation function and it's derivative can affect the training outcome. The method is simulated at a well known benchmark, namely the three tank system, and is incorporated in a Fault Detection and Identification (FDI) method, also applied and simulated at the three tank system. Finally, a comparison is made with an approach that utilizes local model neural networks for system modeling.
暂无评论