A Rapid Two-Step Learning Algorithm for Spline Activation Function Neural Networks with the Application on Biped Gait Recognition

机译：花键激活函数神经网络的快速两步学习算法在双足步态识别中的应用

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

A fast two-stage learning algorithm is proposed to construct and optimize the weights of spline activation function neural networks (SAFNN). Feedforward network is firstly trained by back propagate (BP) algorithm, and then errors are applied to generate new neurons in hidden layers. A rapid dynamic updating algorithm is introduced to modify the new weights. Generalization capability and approximation precision are ensured by the two steps respectively. Simulation results on biped gaits demonstrate improvements in these two capabilities and of learning speed with comparison to traditional BP in SFANN and common NN.

机译：提出了一种快速的两阶段学习算法来构造和优化样条激活函数神经网络（SAFNN）的权重。前馈网络首先通过反向传播（BP）算法进行训练，然后应用错误在隐藏层中生成新的神经元。引入了快速动态更新算法来修改新的权重。这两个步骤分别确保了泛化能力和逼近精度。与SFANN和普通NN中的传统BP相比，在两足动物步态上进行的仿真结果证明了这两种功能的改进以及学习速度的提高。

著录项

来源
《International Symposium on Neural Networks pt.1; 20040819-20040821; Dalian; CN》|2004年|P.286-292|共7页
会议地点 Dalian(CN);Dalian(CN)
作者
Lingyun Hu; Zengqi Sun;
展开▼
作者单位

State Key Laboratory of Intelligent Technology and Systems, Computer Science and Technology Department, Tsinghua University, Beijing, China, 100084;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类计算机网络;
关键词

相似文献

外文文献
中文文献
专利

1. A fuzzy hybrid learning algorithm for radial basis function neural network with application in human face recognition [J] . Haddadnia J., Faez K., Ahmadi M. Pattern Recognition: The Journal of the Pattern Recognition Society . 2003,第5期

机译：径向基函数神经网络的模糊混合学习算法及其在人脸识别中的应用
2. Performance comparison of artificial neural networks learning algorithms and activation functions in predicting severity of autism [J] . Yamini Chand, Afroz Alam, Y. R. S. N. Tejaswini Network Modeling Analysis in Health Informatics and Bioinformatics . 2015,第1期

机译：人工神经网络学习算法和激活函数在预测自闭症严重程度方面的性能比较
3. Functional recognition imaging using artificial neural networks: applications to rapid cellular identification via broadband electromechanical response [J] . MPNikiforov, V V Reukov, G L Thompson, Nanotechnology . 2009,第40期

机译：使用人工神经网络的功能识别成像：通过宽带机电响应在快速细胞识别中的应用
4. A Rapid Two-Step Learning Algorithm for Spline Activation Function Neural Networks with the Application on Biped Gait Recognition [C] . Lingyun Hu, Zengqi Sun International Symposium on Neural Networks . 2004

机译：一种快速的两步学习算法，用于样条动态函数神经网络与Biped Gait识别应用
5. A novel algorithm for neural network implementation of Boolean functions and its application to character recognition [D] . Hussain, Basit. 1991

机译：布尔函数神经网络实现的新算法及其在字符识别中的应用
6. Functional Recognition Imaging Using Artificial Neural Networks: Applications to Rapid Cellular Identification by Broadband Electromechanical Response [O] . M.P. Nikiforov, V.V. Reukov, G.L. Thompson, -1

机译：功能识别成像人工神经网络：应用程序以快速蜂窝式识别通过宽带机电响应
7. Learning Activation Functions in Deep (Spline) Neural Networks [O] . Pakshal Bohra, Joaquim Campos, Harshit Gupta, 2020

机译：深度（样条曲线）神经网络中的学习激活功能
8. Recognition of Lower Limb Movements by Artificial Neural Network for Restoring Gait of Hemiplegic Patients by Functional Electrical Stimulation. [R] . Watanabe, T., Yamagishi, S., Murakami, H., 2001

机译：人工神经网络用于功能性电刺激恢复偏瘫患者步态的下肢运动识别。

A Rapid Two-Step Learning Algorithm for Spline Activation Function Neural Networks with the Application on Biped Gait Recognition

摘要

著录项

相似文献

相关主题

期刊订阅