A recursive prediction error algorithm which converges fast is applied to tra.
采用了收敛速度较快的递推预报误差算法训练神经网络。
Through comparing their sums of squared error, it was concluded that prediction error algorithm-based OE model has the best precision.
通过误差平方和的比较，确定利用基于输出误差（OE）模型的预报误差法所建立的模型的精度最高。
To overcome the slow convergence of the BP algorithm, recursive prediction error algorithm is proposed, which can train both the weight and the bias.
本文介绍了动态对角递归网络，并针对BP算法收敛慢的缺点，将递推预报误差学习算法应用到神经网络权值和域值的训练。
Position prediction algorithm is introduced to compensate the position error in the sampling time, or the extra torque ripple would be produced.
针对采样周斯内的位置误差会引起电机额外的转矩波动，本文引入了位置预测算法。
In simulation, with the same number of parameters, the new algorithm gets better approximation precision and less prediction error than those of the hinge-finding algorithm.
仿真实验表明，在参数个数相同的情况下，使用新模型的逼近算法在逼近精度与预测误差两方面都优于使用原模型。
A novel electrocardiogram compression algorithm based on minimum root-mean-square error prediction utilizing the correlation of adjacent QRS wave is proposed.
本文提出了一种利用相邻QRS波的相关性进行最小均方差预测的心电图压缩算法。
Combining wavelet analysis and neural network characteristics, the error back propagation wavelet neural network based structure and algorithm to ship roll time series prediction are given.
结合小波分析和神经网络的特点，建立了应用于船舶横摇运动时间序列预报的误差反传小波神经网络结构并给出了算法。
The detection algorithm based on chaotic prediction error is used to detect objects under a chaotic background.
基于混沌预测误差的目标检测算法是检测混沌背景下目标的算法。
This algorithm USES the prediction error threshold to retain the useful information to decrease sample training scale.
该算法利用预测误差阈值进行样本的取舍，在尽量保留有用信息的情况下减小样本训练规模。
This algorithm employed full-enclosing prediction based on a new high efficient sorting technique and results in a forecast error set after sorting, which could embed data with a low distortion.
该算法使用一种新的基于高效排序的全邻预测算法，经过排序以后形成预测误差集合，可以在很低失真度的情况下嵌入数据。
This paper proposed a reversible data hiding algorithm for color images based on prediction error difference expansion and Least Significant Bit (LSB) replacement.
将差值扩展技术应用于彩色图像，提出一种基于预测误差差值扩展和最低有效位(LSB)替换的彩色图像可逆数据隐藏算法。
The structure of a partially connected feed forward neural network and the training algorithm based on the recursive prediction error are constructed.
构造了局部连接的前馈神经网络的结构和基于递推预报误差的网络训练算法；
A new algorithm for adaptive prediction error filter is presented.
本文提出一种自适应预测滤波器的新算法。
MinkowskiMethod algorithm, Prediction Error Method for Parameter Identification - the idea of relaxation, it draws on principal component analysis algorithm (PCA).
MinkowskiMethod算法，预报误差法参数辨识-松弛的思想，借鉴了主成分分析算法(PCA)。
A cost function is presented, and by applying Gaussian-Newton type recursive prediction error based method, a stable and efficient online frequency estimation algorithm is derived.
在此基础上，建立了最小方差损失函数，并结合高斯·牛顿预测误差方法，提出了稳定的，高性能的，在线的复频率直接估计算法。
A cost function is presented, and by applying Gaussian-Newton type recursive prediction error based method, a stable and efficient online frequency estimation algorithm is derived.
在此基础上，建立了最小方差损失函数，并结合高斯·牛顿预测误差方法，提出了稳定的，高性能的，在线的复频率直接估计算法。
应用推荐