.png){kind=icon}
返回
Adaptive stepsize estimation based accelerated gradient descent algorithm for fully complex-valued neural networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2023.121166.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Nesterov accelerated gradient (NAG) method is an efficient first-order algorithm for optimization problems. To ensure the convergence, it usually takes a relatively conservative constant as the stepsize. However, the choice of stepsize has a great impact on the optimization process. In this paper, two adaptive stepsize estimation methods are proposed for complex-valued NAG algorithm for efficient training of fully complex-valued neural networks. The basic idea of the first one is to adaptively determine suitable stepsize by estimating the local smoothness constant of the loss function with the norm of approximate complex Hessian matrix. Its validity is theoretically analyzed by means of the decomposition of complex matrix. Furthermore, by introducing a new parameter design method for multi-step quasi-Newton condition, an improved stepsize estimation is presented. Experimental results on pattern recognition, channel equalization, wind forecasting and synthetic aperture radar (SAR) target classification demonstrate the effectiveness of the proposed methods.
Keyword:
Accelerated gradient descent
Adaptive stepsize
Local smoothness constant
Curvature information
Fully complex-valued neural networks
期刊
IF:
7.5
论文数:
3.0W
被引数:
10.2W
机构
引用论文
Animal Welfare and Parasite Infections in Organic and Conventional Dairy Farms: A Comparative Pilot Study in Central Italy.png)
Animals
OAAI
AnimalsIF0
OAAI分享收藏On the use of the atomic force microscope to monitor physical degradation of polymeric coating surfaces关于使用原子力显微镜监测聚合物涂层表面的物理降解
PREAI
分享收藏Mapping and DNA sequence characterisation of the Rysto locus conferring extreme virus resistance to potato cultivar ‘White Lady’PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification复值卷积神经网络及其在极化SAR图像分类中的应用
PREAI
分享收藏Is a Complex-Valued Stepsize Advantageous in Complex-Valued Gradient Learning Algorithms?复值步长在复值梯度学习算法中是有利的吗？
PREAI
分享收藏
查看更多内容