Stability Analysis Based on Caputo-Type Fractional-Order Quantum Neural Networks

Abstract

In this paper, a quantum neural network with multilayer activation function is proposed by using multilayer Sigmoid function superposition and learning algorithm to adjust quantum interval. On this basis, the quasiuniform stability of fractional quantum neural networks with mixed delays is studied. According to the order of two different cases, the conditions of quasi uniform stability of networks are given by using the techniques of linear matrix inequality analysis, and the sufficiency of the conditions is proved. Finally, the feasibility of the conclusion is verified by experiments.

Integrating freelance models with fractional derivatives, and artificial neural networks: A comprehensive approach to advanced computation

“…In a recent work, ANN provided a robust model for the prediction of the drought due to climate change better than statistical, physical and data-driven forecast models. Since the droughts are by nature multivariate and non-linear, and ANN can very efficiently and easily capture the dynamical relationships, therefore ANN is more suitable for drought prediction then contemporary techniques [ 6 ]. ANN can also be used to detect the breast cancer early and its results are way better than Naïve Bayes Algorithm [ 7 ].…”