gradient descent
英 [ˈɡreɪdiənt dɪˈsent]
美 [ˈɡreɪdiənt dɪˈsent]
梯度下降
双语例句
- 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。 - 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。 - Simulation and Experimental Investigation on Coherent Beam Combination of Two Fiber Amplifiers Based on Stochastic Parallel Gradient Descent Algorithm
随机并行梯度下降算法模拟两路光纤放大器相干合成与实验研究 - Beam Cleanup Experiments for Master Oscillator Power Amplifier Laser System by Adaptive Optics Based on Stochastic Parallel Gradient Descent Algorithm
随机并行梯度下降自适应光学对主振荡功率放大器激光系统的光束净化实验 - In order to solve the problem of optimizing the control rules of fuzzy controller on-linely and real-timely, a new approach based on gradient descent algorithm is proposed.
利用梯度下降法反向修改带有可调整因子的模糊控制器中的可调整因子。提出了一种对可调整因子进行在线实时修改和优化的方法。 - Application of Improved Gradient Descent by BP Algorithm to Groundwater Level Forecast
改进梯度下降BP算法在地下水位预测中的应用 - Optimization of Heat Treatment of 7003 Aluminum Alloy Based on BP Neural Networks Gradient Descent Algorithms
基于BP神经网络梯度下降算法的7003铝合金热处理工艺优化 - 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 - Therefore, this article puts forward to new dynamic neural networks with integrator and adjustable feedback coefficient and gets its learning algorithms by gradient descent.
为此，提出了一种由带有积分器和可调反馈系数的神经元构成的动力学神经网络，并利用梯度下降法得到了网络的学习算法。 - Thorax multimodal medical image registration based on adaptive free-form deformation and gradient descent
基于自适应自由变形法和梯度下降法的胸部多模医学图像配准 - Dynamicalsimulation on coherent beam combining of multiple fiber amplifiers based on stochastic parallel gradient descent ( SPGD) algorithm is carried out.
计算结果可为SPGD算法应用至多路高功率光纤放大器相干合成提供参考。 - Image restoration algorithm based on primal-dual hybrid gradient descent method
基于原&对偶混合梯度下降法的图像恢复算法 - Convergence of Batch Gradient Descent Algorithm for High Order Double Parallel Neural Networks
高阶双并联神经网络批处理梯度算法收敛性 - And the three optimization problems are solved respectively by the conjugate gradient method, the adaptive bivariate shrinking and the gradient descent method.
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。 - Performances Index and Convergence Speed of Parallel Gradient Descent Algorithm in Adaptive Optics of Point Source
点目标成像自适应光学随机并行梯度下降算法性能指标与收敛速度 - BP neural network, as its nature of gradient descent method, is easy to fall into local optimum.
但BP神经网络本质是梯度下降法，容易陷入局部最优。 - This paper researches the application of the stochastic parallel gradient descent ( SPGD) optimization algorithm on the beam cleanup system.
就随机并行梯度下降（SPGD）最优化算法在光束净化系统中的应用展开研究。 - This algorithm uses gradient descent method to adjust the measure and the pan coefficient and uses Kalman method to adjust weights. In the end, take dynamic nonlinear system and chaos system as examples to emulate and compare it to other methods.
该算法使用梯度下降方法调整尺度和平移系数，用Kalman方法调整权重，以动态非线性系统和混沌系统为实例做了仿真，并与其它方法做了比较。 - A weight-learning algorithm is presented using the gradient descent method with batch process and adding a momentum item.
在神经网络中采用批处理加动量项的梯度下降算法学习。 - Based on prediction of searching starting-point and gradient searching, the paper proposes a square gradient descent searching algorithm.
基于搜索起点预测和梯度搜索，本文提出了正方形梯度下降搜索算法（SGDS）。 - This paper studies BP network, realizes the method of gradient descent, gets better result than traditional one.
本文研究了BP网络，实现了梯度下降法的网络训练方法，获得了较传统方法好的效果。 - It uses genetic algorithm for optimizing intrinsic parameters and gradient descent method for optimizing extrinsic parameters.
该标定方法内部参数的优化使用遗传算法，外部参数的优化使用梯度下降法，它具有原理简单、不需要估计初始值、鲁棒性强、标定参数更准确的优点。 - The method can not only prune the redundant and conflicted initial fuzzy rules, but also resolve the conflicts of convergence speed and oscillation existing in gradient descent method by introducing dynamic error transfer factor.
该方法不仅能够修剪冗余和冲突的初始模糊规则，而且通过引入动态误差传递因子，解决了梯度下降法中存在的收敛速度和振荡之间的冲突问题。 - 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。 - A Fast Learning Method of Fuzzy Systems Based on GA and Gradient Descent Method
一种基于GA和梯度下降法的快速模糊系统学习方法 - The experiments also show that the gradient descent algorithm based on RM bound is not suitable for some data.
研究同时表明基于RM界的梯度方法对某些数据无效。 - There are relatively typical methods to determine Gaussian kernel parameters σ such as gradient descent and cross validation.
确定高斯核参数σ比较典型的方法有梯度下降法与交叉验证法等。 - Gradient descent with momentum was employed in training the network to provide faster convergence.
网络训练时采用附加动量因子的梯度下降算法，加快了网络的收敛速度。 - In this study, we propose the fuzzy identification approach based on gradient descent theory and employ a new temperature control method which using fuzzy system.
本文提出了采用基于梯度下降法的模糊辨识的方法来对被控对象进行建模，采用模糊系统来对温度进行控制的新方法。 - Secondly, to adjust the PID three weight coefficient by using the gradient descent algorithm.
其次，用最速下降法对PID三个权系数进行调整。