文献类型：期刊文献

英文题名：ACGND: towards lower complexity and fast solution for dynamic tensor inversion

作者：Ye, Aiping[1];Xiao, Xiuchun[2];Xiao, Hua[2];Jiang, Chengze[3];Lin, Cong[2]

机构：[1]Guangdong Ocean Univ, Sch Math & Comp, Zhanjiang 524088, Peoples R China;[2]Guangdong Ocean Univ, Sch Elect & Informat Engn, Zhanjiang 524088, Peoples R China;[3]Southeast Univ, Sch Cyber Sci & Engn, Nanjing 211189, Peoples R China

年份：2024

卷号：10

期号：5

起止页码：6143

外文期刊名：COMPLEX & INTELLIGENT SYSTEMS

收录：SCI-EXPANDED(收录号：WOS:001236081400001)、、Scopus(收录号：2-s2.0-85194741513)、WOS

基金：This work was supported in part by the Stable Supporting Fund of Acoustic Science and Technology Laboratory under Grant JCKYS2024604SSJS00301, in part by the Characteristic Innovation Program of the Education Department of Guangdong Province under Grant 2022KTSCX050.

语种：英文

外文关键词：Dynamic Tensor Inversion (DTI); Adaptive Coefficient Gradient Neural Dynamics (ACGND); Gradient-type Neural Dynamics (GND); Zeroing-type Neural Dynamics (ZND)

外文摘要：Dynamic Tensor Inversion (DTI) is an emerging issue in recent research, prevalent in artificial intelligence development frameworks such as TensorFlow and PyTorch. Traditional numerical methods suffer significant lagging error when addressing this issue. To address this, Zeroing-type Neural Dynamics (ZND) and Gradient-type Neural Dynamics (GND) are employed to tackle the DTI. However, these two methods exhibit inherent limitations in the resolution process, i.e. high computational complexity and low solution accuracy, respectively. Motivated by this technology gap, this paper proposes an Adaptive Coefficient Gradient Neural Dynamics (ACGND) for dynamically solving the DTI with an efficient and precise manner. Through a series of simulation experiments and validations in engineering applications, the ACGND demonstrates advantages in resolving DTI. The ACGND enhances computational efficiency by circumventing matrix inversion, thereby reducing computational complexity. Moreover, its incorporation of adaptive coefficients and activation functions enables real-time adjustments of the computational solution, facilitating rapid convergence to theoretical solutions and adaptation to non-statinary scenarios. Code is available at https://github.com/Maia2333/ACGND-Code-Implementation.