误差反传算法 meaning in English
error back propagation algorithm
Examples
- Design of on - line learning based error back propagation algorithm in simulation servo system
基于在线学习误差反传算法的仿真伺服系统设计 - Chapter 4 presents an error back propagation algorithm with quadratic momentum of the multilayer forward neural networks that will speed up the error convergence velocity
本文提出一种带二次动量项的多层前向网络误差反传算法，提高了神经网络的误差收敛速度。 - Feature extraction through 2 - order polynomial fit of the descending part of the response curve made possible a timesaving measurement process . the performances of two pattern recognition algorithms , namely principal component analysis ( pca ) and linear discriminant analysis ( lda ) in practical problems were discussed . artificial neural network ( ann ) was utilized with back - propagation algorithm ( bpa ) , and the combination of pca / lda with ann improved the identification performance of the system
基于对模式识别系统的深入研究，提出了从响应阶段数据提取特征的方法，节省了测试所需时间；比较了主成分分析法( principalcomponentanalysis , pca )与线性判别式法( lineardiscriminantanalysis , lda )两种模式识别方法在实际应用中的不同结果，分析了原因；设计了采用误差反传算法back - propagationalgorithm , bpa )的前向人工神经网络( artificialneuralnetwork , ann ) ，并指出其应用中存在的问题，提出了改进建议；利用pca lda与ann相结合的方法改善了系统的识别性能。 - 5 based on studying artificial nerve network theory , establish the nerve network model of cutting parameter . use back propagation algorithm ( bp algorithm ) as system ' s nerve network learning method . system has realized cutting parameter nerve network intelligentized choosing function
5在深入研究人工神经网络理论的基础上，建立了切削参数选择的神经网络模型，采用误差反传算法(即算法)作为切削参数智能选择的神经网络学习方法，实现了切削参数人工神经网络智能选择功能。 - The simulation results indicate the capability of genetic algorithm in fast and steady learning of neural networks , guaranteeing a global convergence and overcoming some shortcomings of traditional error back propagation algorithms , meanwhile prove that this neural networks adaptive control structure is effective to many control problems and it is easy for us to programme and employ the method in the practical system
仿真结果表明遗传算法能够快速稳定地学习神经网络，保证全局收敛西安理工大学硕士学位论文并且能够克服传统误差反传算法的一些缺点，也证明了这种神经网络自适应控制结构可以有效解决系统中存在的控制难题，同时编程容易，便于在实际系统中应用。