gradient descent

Study on Adaptive Fuzzy Control System Based on Gradient Descent Learning Algorithm

基于梯度下降法的自适应模糊控制系统研究

A robust speech recognition system based on discriminative learning of environmental features is proposed for recognition of environmental features in high noise background, and a gradient descent algorithm was adopted for parameters optimization.

介绍了一种环境特征判别学习的Robust语音识别方法，该方法基于最小分类错误准则利用梯度下降法迭代地学习环境特征，实现了高噪声背景下命令语音识别系统。

It can be solved by iteration of gradient descent.

它通过梯度下降迭代求得最小值.

On the basis of data mining, a new self-learning fuzzy method is developed to model and predict chaotic time series, by means of interest measure and improved gradient descent method.

基于数据挖掘思想，使用兴趣度度量和改进的梯度下降法，提出一种新的、具有自学习能力的模糊方法来建模和预测混沌时间序列。

Stochastic parallel gradient descent algorithm for adaptive optics system based on Zernike mode

基于Zernike模式的自适应光学系统随机并行梯度下降算法

The tread of warrant theoretical price which is calculated by RBF network model based on K-means clustering algorithm 、 gradient descent and particle swarm optimization algorithm and the actual price is same. 3.

基于K-均值聚类算法、梯度下降算法和PSO算法优化的RBF网络模型计算的权证理论价格与实际价格的趋势基本一致。

A new gradient descent algorithm for unconstrained optimization problem is proposed.

提出了一种新的无约束优化下降算法.

The scoring model uses concepts both in positive example set and negative example set to guide the selection process, and adopts active learning strategy with stochastic gradient descent algorithm to update parameter.

打分模型使用正例概念集合和反例概念集合来引导筛选过程，采用主动学习策略结合随机梯度下降算法更新参数。

Gradient descent algorithm using momentum BP network training.

采用动量梯度下降算法训练BP网络.

Nonlinear Gradient Descent Algorithm Theories and Its Analysis for the Stability of Hopfield Network

非线性梯度下降算法理论及其对Hopfield网络稳定性的分析

Training networks combining genetic algorithm ( GA) based on global optimization with backpropagation ( BP) based on gradient descent in the paper make the linking weights of networks self-adaptive evolution in constantly iterative process.

本文采用全局寻优的遗传算法（GA）和基于梯度下降的局部寻优反传算法（BP）相结合来训练网络，使网络的连接权在不断迭代过程中自适应演化。

A fuzzy supplementary controller is designed for UPFC to damp tie line power oscillation in interconnected power systems. The parameters of FDC ( Fuzzy Damping Controller) are optimized using the gradient descent training method and the genetic algorithm respectively.

设计了一种统一潮流控制器（UPFC）模糊辅助控制器，能够阻尼互联系统之间功率低频振荡，分别使用遗传算法和梯度下降法实现了模糊阻尼控制器（FDC）的参数优化。

We compare of convergence speed and networks output errors of tangent planes to constraint surface algorithm and gradient descent algorithm in the training of neural networks and draw the conclusion that the tangent planes algorithm converges speedily under the same circumstance.

我们比较了梯度下降和限制平面的切平面两种算法在训练人工神经网络时的收敛速度和网络输出误差，得到了在相同条件下，切平面法比梯度下降法收敛得更快的结论。

For the learning process, a new kind of empirical risk function is proposed which is differentiable and can be minimized by gradient descent strategy.

对于参数的学习，提出了一种适用于分类器的可微经验风险函数，该函数能够有效地利用梯度下降法进行最小化。

The four interferences are avoided effectively by elaborately constructing the energy function, the total channel number is minimized by the gradient descent searching algorithm.

为了有效地避免这四种干扰，算法精心地构建了NCNN能量函数，并通过梯度下降的办法，最小化了总的信道数目。

Based on gradient descent rule, the BP ( Back Propagation ) algorithm is a local optimization algorithm.

bp 算法基于梯度下降原理,是一种局部寻优算法.

Finally, all of the parameters of the T-S model are determined accurately with gradient descent algorithm.

最后, 通过梯度下降方法,精确确定T -S 模糊模型的所有参数.

After having obtained the Euler-Lagrange equation of the threshold model, we compute this equation numerically by the method of gradient descent flows.

在得到门限模型的Euler-Lagrange方程后，我们利用梯度下降法实现数值计算。

After making full analysis about various parameters of the BP neural network, The LM ( Levenberg-Marquardt) optimization algorithm is cited to replace the traditional steepest gradient descent method as the BP neural network training function.

在对BP神经网络的各个参数进行充分分析后，引用了LM（Levenberg-Marquardt）经典优化算法来取代传统的最速梯度下降法作为BP网络的训练函数。

A class of descent methods based on conjugate gradient method

一类基于共轭梯度法的下降算法

The weights are trained with Gradient Descent Method. The increase algorithm of BVS, and restricted algorithm, was induced.

利用梯度下降法对网络的权值进行训练，并且推导了BVS的增长算法，以及网络训练的限制记忆递推公式。

So we can use the convolution of Laplacian operator to compute the gradient descent.

因此,可以利用有向拉普拉斯算子的卷积来计算梯度下降迭代公式.

A new design algorithm of FIR filters is proposed based on above two notions, which uses the steepest gradient descent ( SGD) algorithm to correct the coefficients of optimum MMSE filters iteratively to achieve the optimum result.

基于上述两种设计理念，提出了一种新的FIR滤波器设计算法。该算法采用最陡梯度下降法来对平方误差最小化下的最佳滤波器系数进行迭代修正，得到最佳结果。

Consider water level of boiler drum as the object for study, find out the proper variables as input of the ANN ( Artificial Neural Network) throughout the analysis of the inner mechanism. The function of learning was realized using K-means Cluster method and Gradient Descent Algorithm.

以汽包水位为对象.结合机理分析确定原始变量作为神经网络的输入.通过k均值聚类法则与梯度下降法实现了网络的学习功能.并最终建立了基于RBF神经网络的软测量模型。

The delta rule is based on the idea of gradient descent.

而delta规则是基于梯度降落这样一种思路。

The iteration process is replaced by the PSO based on the gradient descent of FCM, which makes the algorithm have a strong global searching capacity and avoids the local minimum problems of FCM.

新算法用PSO算法代替了FCM算法的基于梯度下降的迭代过程，使算法具有很强的全局搜索能力，很大程度上避免了FCM算法易陷入局部极小的缺陷；

An on line learning algorithm based on the error gradient descent method is proposed. the stability of closed loop system is proved in Lyapunov ′ s sense.

为此提出一种基于对角递归神经网络的非线性噪声有源自适应控制方法，并给出一种基于误差梯度下降的在线学习算法，同时证明了闭环控制系统在Lyapunov意义下的稳定性。