Yiqun Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yiqun Zhang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Gang Lin
School of Design, Fujian University of Technology
2 shared publications - Honglei Xu
School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth, Australia
2 shared publications - Chaoyang Tao
School of Electrical Engineering, Computation and Mathematical Sciences, Curtin University, Kent Street, Perth, WA 6102, Australia
1 shared publication - Che Shen
Graduate School of Global Environmental Studies, Sophia University, Tokyo, 1028554, Japan
1 shared publication - Liyuan Zhang
School of Electrical Engineering, Computation and Mathematical Sciences, Curtin University, Kent Street, Perth, WA 6102, Australia
1 shared publication - Qiuyi Zhang
College of Architecture and Urban Planning, Fujian University of Technology, Fuzhou, China
1 shared publication
Latest Publications
- Open Access
- 20 May 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (5) , 220
An Integer-Fractional Gradient Algorithm for Back Propagation Neural Networks
This paper proposes a new optimization algorithm for backpropagation (BP) neural networks by fusing integer-order differentiation and fractional-order differentiation, while fractional-order differentiation has significant advantages in describing complex phenomena with long-term memory effects and nonlocality, its application in neural networks is often limited by a lack of physical interpretability and inconsistencies with traditional models. To address these challenges, we propose a mixed integer-fractional (MIF) gradient descent algorithm for the training of neural networks. Furthermore, a detailed convergence analysis of the proposed algorithm is provided. Finally, numerical experiments illustrate that the new gradient descent algorithm not only speeds up the convergence of the BP neural networks but also increases their classification accuracy.
- 20 May 2024
- Published by MDPI AG in Algorithms
- Vol. 17 (5) , 220
Open AccessAn Integer-Fractional Gradient Algorithm for Back Propagation Neural Networks
This paper proposes a new optimization algorithm for backpropagation (BP) neural networks by fusing integer-order differentiation and fractional-order differentiation, while fractional-order differentiation has significant advantages in describing complex phenomena with long-term memory effects and nonlocality, its application in neural networks is often limited by a lack of physical interpretability and inconsistencies with traditional models. To address these challenges, we propose a mixed integer-fractional (MIF) gradient descent algorithm for the training of neural networks. Furthermore, a detailed convergence analysis of the proposed algorithm is provided. Finally, numerical experiments illustrate that the new gradient descent algorithm not only speeds up the convergence of the BP neural networks but also increases their classification accuracy.