Xiaojun Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaojun Zhou has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Chunna Zhao
School of Information Science and Engineering, Yunnan University, Kunming, China
7 shared publications Yaqun Huang
6 shared publicationsChengli Zhou
3 shared publicationsJunjie Ye
3 shared publications- Junjie Ye
School of Information Science & Engineering, Yunnan University, Kunming, Yunnan, 650221, China
3 shared publications Kemeng Xiang
3 shared publications
Latest Publications
- 23 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 708
Robust fractional-order automatic differentiation and its applications in neural networks
- 23 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 708
Robust fractional-order automatic differentiation and its applications in neural networks
- 22 December 2025
- Published by Elsevier in Neurocomputing
- Vol. 669
Fractional-order matrix differentiation and its application in artificial neural networks
- 22 December 2025
- Published by Elsevier in Neurocomputing
- Vol. 669
Fractional-order matrix differentiation and its application in artificial neural networks
- Open Access
Fractional-order Jacobian Matrix Differentiation and Its Application in Artificial Neural Networks
Fractional-order differentiation has many characteristics different from integer-order differentiation. These characteristics can be applied to the optimization algorithms of artificial neural networks to obtain better results. However, due to insufficient theoretical research, at present, there is no fractional-order matrix differentiation method that is perfectly compatible with automatic differentiation (Autograd) technology. Therefore, we propose a fractional-order matrix differentiation calculation method. This method is introduced by the definition of the integer-order Jacobian matrix. We denote it as fractional-order Jacobian matrix differentiation (${\bf{J}^α}$). Through ${\bf{J}^α}$, we can carry out the matrix-based fractional-order chain rule. Based on the Linear module and the fractional-order differentiation, we design the fractional-order Autograd technology to enable the use of fractional-order differentiation in hidden layers, thereby enhancing the practicality of fractional-order differentiation in deep learning. In the experiment, according to the PyTorch framework, we design fractional-order Linear (FLinear) and replace nn.Linear in the multilayer perceptron with FLinear. Through the qualitative analysis of the training set and validation set $Loss$, the quantitative analysis of the test set indicators, and the analysis of time consumption and GPU memory usage during model training, we verify the superior performance of ${\bf{J}^α}$ and prove that it is an excellent fractional-order gradient descent method in the field of deep learning.Open AccessFractional-order Jacobian Matrix Differentiation and Its Application in Artificial Neural Networks
Fractional-order differentiation has many characteristics different from integer-order differentiation. These characteristics can be applied to the optimization algorithms of artificial neural networks to obtain better results. However, due to insufficient theoretical research, at present, there is no fractional-order matrix differentiation method that is perfectly compatible with automatic differentiation (Autograd) technology. Therefore, we propose a fractional-order matrix differentiation calculation method. This method is introduced by the definition of the integer-order Jacobian matrix. We denote it as fractional-order Jacobian matrix differentiation (${\bf{J}^α}$). Through ${\bf{J}^α}$, we can carry out the matrix-based fractional-order chain rule. Based on the Linear module and the fractional-order differentiation, we design the fractional-order Autograd technology to enable the use of fractional-order differentiation in hidden layers, thereby enhancing the practicality of fractional-order differentiation in deep learning. In the experiment, according to the PyTorch framework, we design fractional-order Linear (FLinear) and replace nn.Linear in the multilayer perceptron with FLinear. Through the qualitative analysis of the training set and validation set $Loss$, the quantitative analysis of the test set indicators, and the analysis of time consumption and GPU memory usage during model training, we verify the superior performance of ${\bf{J}^α}$ and prove that it is an excellent fractional-order gradient descent method in the field of deep learning. - 17 May 2025
- Published by Elsevier in Neural Networks
- Vol. 189, 107588
Dual-stream interactive networks with pearson-mask awareness for multivariate time series forecasting
- 17 May 2025
- Published by Elsevier in Neural Networks
- Vol. 189, 107588
Dual-stream interactive networks with pearson-mask awareness for multivariate time series forecasting
- 1 December 2024
- Published by Elsevier in Neural Networks
- Vol. 183, 106970
Improved fractional-order gradient descent method based on multilayer perceptron
- 1 December 2024
- Published by Elsevier in Neural Networks
- Vol. 183, 106970
Improved fractional-order gradient descent method based on multilayer perceptron
- Open Access
- 7 January 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (2) , 316
A Deep Learning Optimizer Based on Grünwald–Letnikov Fractional Order Definition
In this paper, a deep learning optimization algorithm is proposed, which is based on the Grünwald–Letnikov (G-L) fractional order definition. An optimizer fractional calculus gradient descent based on the G-L fractional order definition (FCGD_G-L) is designed. Using the short-memory effect of the G-L fractional order definition, the derivation only needs 10 time steps. At the same time, via the transforming formula of the G-L fractional order definition, the Gamma function is eliminated. Thereby, it can achieve the unification of the fractional order and integer order in FCGD_G-L. To prevent the parameters falling into local optimum, a small disturbance is added in the unfolding process. According to the stochastic gradient descent (SGD) and Adam, two optimizers’ fractional calculus stochastic gradient descent based on the G-L definition (FCSGD_G-L), and the fractional calculus Adam based on the G-L definition (FCAdam_G-L), are obtained. These optimizers are validated on two time series prediction tasks. With the analysis of train loss, related experiments show that FCGD_G-L has the faster convergence speed and better convergence accuracy than the conventional integer order optimizer. Because of the fractional order property, the optimizer exhibits stronger robustness and generalization ability. Through the test sets, using the saved optimal model to evaluate, FCGD_G-L also shows a better evaluation effect than the conventional integer order optimizer.
- 7 January 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (2) , 316
Open AccessA Deep Learning Optimizer Based on Grünwald–Letnikov Fractional Order Definition
In this paper, a deep learning optimization algorithm is proposed, which is based on the Grünwald–Letnikov (G-L) fractional order definition. An optimizer fractional calculus gradient descent based on the G-L fractional order definition (FCGD_G-L) is designed. Using the short-memory effect of the G-L fractional order definition, the derivation only needs 10 time steps. At the same time, via the transforming formula of the G-L fractional order definition, the Gamma function is eliminated. Thereby, it can achieve the unification of the fractional order and integer order in FCGD_G-L. To prevent the parameters falling into local optimum, a small disturbance is added in the unfolding process. According to the stochastic gradient descent (SGD) and Adam, two optimizers’ fractional calculus stochastic gradient descent based on the G-L definition (FCSGD_G-L), and the fractional calculus Adam based on the G-L definition (FCAdam_G-L), are obtained. These optimizers are validated on two time series prediction tasks. With the analysis of train loss, related experiments show that FCGD_G-L has the faster convergence speed and better convergence accuracy than the conventional integer order optimizer. Because of the fractional order property, the optimizer exhibits stronger robustness and generalization ability. Through the test sets, using the saved optimal model to evaluate, FCGD_G-L also shows a better evaluation effect than the conventional integer order optimizer.