Recent Advances and Applications of Fractional-Order Neural Networks

Abstract

This paper focuses on the growth, development, and future of various forms of fractional-order neural networks. Multiple advances in structure, learning algorithms, and methods have been critically investigated and summarized. This also includes the recent trends in the dynamics of various fractional-order neural networks. The multiple forms of fractional-order neural networks considered in this study are Hopfield, cellular, memristive, complex, and quaternion-valued based networks. Further, the application of fractionalorder neural networks in various computational fields such as system identification, control, optimization, and stability have been critically analyzed and discussed.