Zobrazeno 1 - 10
of 481
pro vyhledávání: '"Xu, Dongpo"'
We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learning (RTRL) algorithm and the maximum correntropy criterion (MCC) as a
Externí odkaz:
http://arxiv.org/abs/2402.14227
Autor:
Mandic, Danilo P., Talebi, Sayed Pouria, Took, Clive Cheong, Xia, Yili, Xu, Dongpo, Xiang, Min, Bourigault, Pauline
From their inception, quaternions and their division algebra have proven to be advantageous in modelling rotation/orientation in three-dimensional spaces and have seen use from the initial formulation of electromagnetic filed theory through to formin
Externí odkaz:
http://arxiv.org/abs/2311.16771
Adam is a commonly used stochastic optimization algorithm in machine learning. However, its convergence is still not fully understood, especially in the non-convex setting. This paper focuses on exploring hyperparameter settings for the convergence o
Externí odkaz:
http://arxiv.org/abs/2307.11782
Publikováno v:
IEEE Trans. Signal Process., vol. 71, pp. 4106-4115, Oct. 2023
Convex optimization methods have been extensively used in the fields of communications and signal processing. However, the theory of quaternion optimization is currently not as fully developed and systematic as that of complex and real optimization.
Externí odkaz:
http://arxiv.org/abs/2305.06879
Publikováno v:
Neural Computation (2024) 36 (9): 1912-1938
Adam-type algorithms have become a preferred choice for optimisation in the deep learning setting, however, despite success, their convergence is still not well understood. To this end, we introduce a unified framework for Adam-type algorithms (calle
Externí odkaz:
http://arxiv.org/abs/2305.05675
Publikováno v:
Neurocomputing 527 (2023) 27-35
The stochastic momentum method is a commonly used acceleration technique for solving large-scale stochastic optimization problems in artificial neural networks. Current convergence results of stochastic momentum methods under non-convex stochastic se
Externí odkaz:
http://arxiv.org/abs/2205.14811
Publikováno v:
In Neural Networks November 2024 179
Autor:
Wen, Lujie, Ma, Xueyan, Geng, Kaixiang, Lv, Guohua, Jin, Wu, Chen, Wanwen, Xu, Dongpo, Shen, Huaishun, Wen, Haibo
Publikováno v:
In Aquaculture 15 September 2024 590
Autor:
Li, Jiayi, Nie, Zhijuan, Hu, Jiawen, Wang, Lanmei, Song, Chao, Xu, Dongpo, Gao, Jiangcao, Xu, Pao, Xu, Gangchun
Publikováno v:
In Food Chemistry 1 September 2024 451
Publikováno v:
In Signal Processing February 2025 227