Description: bp神经网络算法是解决最优化问题的先进算法之一，本论文讨论了神经网络中使用最为广泛的前馈神经网络。其网络权值学习算法中影响最大的就是误差反向传播算法（back-propagation简称BP算法）。BP算法存在局部极小点，收敛速度慢等缺点。基于优化理论的Levenberg-Marquardt算法忽略了二阶项。该文讨论当误差不为零或者不为线性函数即二阶项S(W)不能忽略时的Hesse矩阵的近似计算，进而训练网络。-bp neural network algorithm to solve optimization problems, one of the advanced algorithm, the paper discusses the neural network in the most widely used feed-forward neural network. Its network weights learning algorithm in the greatest impact is the error back-propagation algorithm (back-propagation algorithm referred to as BP). BP algorithm for the existence of local minimum points, such as the shortcomings of slow convergence. Optimization theory based on the Levenberg-Marquardt algorithm ignores the second-order item. In this paper, the discussion when the error is not zero or not that is second-order linear function of S (W) can not be ignored when the Hesse matrix of approximate calculation, and then training the network. Platform: |
Size: 19456 |
Author:刘慧 |
Hits:
Description: 用bp神经网络的进行函数逼近，达到逼近的效果-Bp neural network used for function approximation to approximate the effects of Platform: |
Size: 1024 |
Author:徐进富 |
Hits:
Description: BP算法例子：用一个五层的神经网络去逼近函数f(x1,x2)=pow(x1-1,4)+2*pow(x2,2)-BP algorithm is an example: with a five-layer neural network to approximate the function f (x1, x2) = pow (x1-1, 4)+2* pow (x2, 2) Platform: |
Size: 31744 |
Author:zhangzhong |
Hits:
Description: 利用神经网络中BP神经网络来拟合要逼近函数的程序。使用BP算法。-The use of neural network to fit the BP neural network to approximate the function procedure. The use of BP algorithm. Platform: |
Size: 6144 |
Author:珊珊 |
Hits:
Description: 实验使用BP神经网络来逼近一个较复杂的正弦函数，并观察BP神经网络的各个参数对BP神经网络的影响.-Experimental use of BP neural network to approximate a more complex sine function, and to observe the parameters of BP neural network on the impact of BP neural network. Platform: |
Size: 491520 |
Author: |
Hits:
Description: 基于BP神经网络算法的函数逼近，利用matlab实现BP算法逼近任意非线性函数-BP neural network algorithm based on function approximation, using matlab to achieve BP algorithm approximate any nonlinear function Platform: |
Size: 1024 |
Author:chrossley |
Hits:
Description: 这是一个径向基函数神经网络，通过RBF网络的学习算法来逼近一个二维函数，并利用LMS算法来进行权值调整。-This is a radial basis function neural network, RBF network learning algorithm adopted to approximate a two-dimensional function, and use of LMS algorithm for weight adjustment. Platform: |
Size: 1024 |
Author:北飞 |
Hits:
Description: 介绍如何通过matlab使用bp神经网络和rbf神经网络来逼近非线性函数-Describes how to use matlab bp neural network and rbf neural networks to approximate nonlinear functions Platform: |
Size: 1024 |
Author:仁杰 |
Hits:
Description: BP神经外那个罗可以逼近任意函数，此为拟合函数的源代码-BP neural network can approximate any function, the source code for the fitting function Platform: |
Size: 1024 |
Author:章颖 |
Hits:
Description: BP神经网络Simulink模型。。例子给了个离散传递函数。训练后的网络可以逼近任意传递函数，或者非线性函数。-Simulink model of BP neural network. . Examples for the discrete transfer function. Trained network can approximate any transfer function, or the nonlinear function. Platform: |
Size: 9216 |
Author:罗波 |
Hits:
Description: RBF神经网络的源程序 遗传RBF网络 RBF神经网络对非线性系统进行逼近-RBF neural network of the source of genetic RBF neural network RBF network to approximate the nonlinear system Platform: |
Size: 2048 |
Author:祁峥东 |
Hits:
Description: 人工神经网络(Artificial Neural Network)是从生理角度对智能的模拟，具有极
高的学习能力和自适应能力，能够以任意精度逼近任意函数，完成对系统的仿真；
而遗传算法是对自然界生物进化过程的模拟，具有极强的全局寻优能力，这两种
算法都是当下研究较多的智能方法。将这两种方法与常规的 PID 控制相结合，
构成智能 PID 控制器，使其具有参数自整定、自适应的能力，以适应复杂环境
下的控制要求，这一思路对提高控制效果具有很好的现实意义。
-Artificial Neural Network (ANN) is an imitation of the intelligence by the point of physiological. It has a high capacity of learning and adaptive, can approximate any function to arbitrary accuracy, and complete the simulation of the system. The Genetic
algorithm is a simulation of natural biological evolution, which has a strong ability of
global optimization. These two algorithms are more intelligent method of current
research. The idea of combining these two methods with the conventional PID
controller to be a intelligent controller with the abilities of parameter auto-tuning and
adaptive for the requirements of the complex environment, has a high practical
significance of improving the control effect.
Platform: |
Size: 661504 |
Author:baijiaxuan |
Hits:
Description: MATLAB语言作为编程工具构造CMAC神经网络，利用公式Wij(k+1)=Wij(k)+β(yid-yi)α/αTα对连接权系数Wij进行调整，用来对正弦函数sin（x）进行逼近-MATLAB programming language as a tool to construct CMAC neural network, using the formula Wij (k+1) = Wij (k)+ β (yid-yi) α/αTα the connection weights Wij to adjust to the sine function sin (x) approximate the Platform: |
Size: 1024 |
Author: |
Hits:
Description: BP神经网络预测模型的非线性逼近功能很好，能够成功的预测复杂的数据结构-The BP neural network model of nonlinear approximate function is very good, can successfully predict complex data structure
Platform: |
Size: 3072 |
Author:张震 |
Hits:
Description: 用前向神经元网络逼近连续函数，f（x1，x2，x3，x4）=sinx1+sinx2+sinx3+sinx4 定义域为[0,2*pi].刘宝碇老师例子仅供参考-Let us design a feedforward NN to approximate the continuous
function,
f(x1, x2, x3, x4) = sin x1+ sin x2+ sin x3+ sin x4
defined on [0, 2*pi]4. Platform: |
Size: 5120 |
Author:李小静 |
Hits:
Description: 产生3000个训练数据，训练一个前向神经元网络对f（x）进行逼近。刘宝碇不确定规划及应用 神经元网络 例3.2-We generate 3000 training data for the function f(x). Then we train a
feedforward NN to approximate the function。 neural networks example 3.2 Platform: |
Size: 5120 |
Author:李小静 |
Hits:
Description: 1.elman神经网络对输入波形进行检测
2.设计具有3个神经元的Hopfield网络
3.建立自适应神经模糊推理系统对非线性函数进行逼近（正弦加滞后）
4.建立自适应神经模糊推理系统对非线性函数进行逼近（正弦多项式）
5.利用模糊C均值聚类方法将一类随机给定的三维数据分为三类(1.Detection of input waveform by elman neural network
2. design a Hopfield network with 3 neurons
3. establish adaptive neuro fuzzy inference system to approximate nonlinear functions (sine plus lag).
4. establish adaptive neuro fuzzy inference system to approximate nonlinear functions (sine polynomials).
5. fuzzy C means clustering method is used to divide a class of randomly given 3D data into three categories.) Platform: |
Size: 2048 |
Author:南风水忆 |
Hits:
Search - neural network approximate