对目标函数进行梯度优化，我们得出了介质速度的迭代公式。
By optimizing the objective function with the gradient method the iterative formula about the medium velocity is obtained.
基于随机有限元的梯度优化算法引入拥有随机参数的框架可靠度分析。
The gradient optimization algorithm based on the stochastic finite element was adopted to analyze the reliability of the frame with stochastic parameters.
神经网络的训练采用一阶梯度优化算法，利用点堆中子动力学模型产生训练样本。
The first order gradient optimization algorithm is employed to train the network. The training samples stem from the neutron kinetics of the point-reactor.
将梯度优化过程看作反馈控制系统，从而提出了一种带动量项的PID梯度算法(PIDGDM)。
An algorithm of PID gradient descent with momentum term (PIDGDM) is proposed. In this algorithm, the procedure of gradient optimization is considered as a feedback control system.
为确定多层人工神经网络的权值和阈值建立了混合求解方法，即迭代前期采用BP算法而迭代后期采用梯度优化法进行计算。
Mixed method is built to calculate the weights and thresholds of multi-layer neural network by utilize BP algorithm and terraced optimizations.
为确定多层人工神经网络的权值和阈值建立了混合求解方法，即迭代前期采用BP算法，而迭代后期采用梯度优化法进行计算。
Mixed method was built to calculate the weights and thresholds of multi-layer neural network by utilize BP algorithm and terraced optimizations.
通过BP算法、梯度优化法和混合算法对相同实例网络权值和阈值的计算，验证了所提出的混合算法的有效性，实现了权值和阈值的快速准确计算。
Comparing mixed method with BP algorithm and terraced method, validity of the method was testified, which results in rapid computing of weights and thresholds.
优化过程中所必要的梯度信息是用伴随网络法获得的。
The gradient information which is required in the optimization process is provided by the adjoint network technique.
无约束优化问题的共轭梯度路径构造的思想启迪我们用其来解带线性等式约束和有界变量约束的优化问题。
The idea of conjugate gradient path in unconstrained optimization irradiates us to use this method for solving the linear equality optimization subject to bounds on variables.
考虑神经网络在训练大规模样品时易陷入局部极小，用梯度下降法与混沌优化方法相结合，使神经网络实现快速训练的同时，避免陷入局部极小。
Combining grading method with chaotic optimization, the neural network model achieves rapid training and avoids local minimum when there are a lot of samples to be trained.
并提出分别采用共轭梯度法、二元自适应收缩法以及梯度下降法对以上优化问题求解。
And the three optimization problems are solved respectively by the conjugate gradient method, the adaptive bivariate shrinking and the gradient descent method.
程序中采用了“共轭梯度——最小二乘”优化方法，其收敛性能较好，在较坏的初值情况下也能较快收敛。
In this program, the optimization method of "Conjugate Gradient-Least Squares" is employed, since it usually gives good convergent results.
在分析电容层析成像基本原理和图像重建算法的基础上，提出一种结合正则化优化修正的共轭梯度算法。
Based on the analysis of basic principle of electrical capacitance tomography and the image reconstruction algorithm, a conjugate gradient algorithm with optimized regularization is proposed.
传统的最优化技术大多是基于梯度寻优技术或随机搜索的方法。
Traditional optimization techniques search for the best solutions using gradients or random searching.
本文使用信赖域策略结合投影梯度算法来解约束优化问题，并给出算法及其收敛性。
This paper is to study the convergence properties of the gradient projection method with trust region strategy for constrained optimization.
该文提出一种无约束优化非线性共轭梯度法，证明了精确线性搜索下的全局收敛性。
The paper presents a nonlinear conjugate gradient method for unconstrained optimization problem, and proves its global convergence under exact line searches.
对于其中的非线性约束采用活动约束集的概念，而对于线性边界约束，则按约束优化方法中的梯度投影法作专门处理。
The active constraint set was introduced in the nonlinear constraints of the optimization, meanwhile the project gradient method was used to treat the linear boundary constraints.
梯度下降法与混沌优化法均具有各自的缺点。
The decreasing gradient algorithm and chaos algorithm both have shortcomings for optimization problems.
本文将数学规划法与优化准则法有机地结合起来，导出了一种新的优化方法——变尺度梯度投影法。
A new nonlinear optimization method called variable metric gradient projection method is presented. It is a combination of mathematical programming with optimality criterion.
共轭梯度法是求解无约束优化问题的一类有效方法。
The conjugate gradient method is one of the most efficient methods for solving unconstrained optimization problems.
提出一种混沌梯度组合全局优化算法，并对该算法进行了收敛性分析。
A coupled optimization algorithm combined gradient search with chaotic search is proposed and its (convergence) is discussed.
本文利用微机通过梯度法初步实现对汽车振动参数的优化设计。
An attempt has been made to apply a gradient method for optimizing motor cars oscillatory parameter using microcomputers.
在此宏观模型的基础上，利用简约梯度法推求各供水泵站优化的工况点。
Based on this macroscopic model, reduced gradient method was applied to search for the optimal working conditions of pumping stations.
利用视差梯度有限约束，优化灰度相关复峰集。
The gray correlation multi-peak set then was optimized by disparity gradient limited constraint.
传统的模糊c -均值(FCM)聚类是一种基于梯度下降的优化算法，该方法对初始化较敏感，且易陷入局部极小。
The traditional fuzzy C-means (FCM) algorithm is an optimization algorithm based on gradient descending. it is sensitive to the initial condition and liable to be trapped in a local minimum.
从而为优化设计和制备梯度功能材料提供了一种可行的实验方法和有意义的结果。
This paper has offered a kind of feasible experiment method and meaningful results to optimum design and manufacturing of functional gradient material.
本文针对传统BP算法存在的两个常见问题进行了讨论，提出了基于步长优化和共轭梯度法的改进BP算法。
This paper discussed two basic problems of conventional BP algorithm. A improved BP algorithm based on step optimum and conjugate gradient was put forword in this paper.
本文针对传统BP算法存在的两个常见问题进行了讨论，提出了基于步长优化和共轭梯度法的改进BP算法。
This paper discussed two basic problems of conventional BP algorithm. A improved BP algorithm based on step optimum and conjugate gradient was put forword in this paper.
应用推荐