Location:
Search - BP 3-6
Search list
Description: 基于C开发的三个隐层神经网络，输出权值、阈值文件，训练样本文件，提供如下函数：1）初始化权、阈值子程序；2）第m个学习样本输入子程序；3）第m个样本教师信号子程序；4）隐层各单元输入、输出值子程序；5）输出层各单元输入、输出值子程序；6）输出层至隐层的一般化误差子程序；7）隐层至输入层的一般化误差子程序；8）输出层至第三隐层的权值调整、输出层阈值调整计算子程序；9）第三隐层至第二隐层的权值调整、第三隐层阈值调整计算子程序；10）第二隐层至第一隐层的权值调整、第二隐层阈值调整计算子程序；11）第一隐层至输入层的权值调整、第一隐层阈值调整计算子程序；12）N个样本的全局误差计算子程序。-C development based on the three hidden layer neural network, the output weights, threshold documents, training sample documents, for the following functions : a) initialization, the threshold subroutine; 2) m learning samples imported subroutine; 3) m samples teachers signal Subroutine ; 4) hidden layer of the module input and output value subroutine; 5) the output layer of the module input and output value subroutine; 6) the output layer to the hidden layer subroutine error of generalization; 7) hidden layer to the input layer subroutine error of generalization; 8) the output layer to the third hidden layer Weight adjustment, the output layer threshold adjustment routines; 9) 3rd hidden layer to the second hidden layer weights adjustment, the third hidden layer threshold adjustment routi
Platform: |
Size: 11264 |
Author: 李洋 |
Hits:
Description: 《遗传算法--理论、应用与软件实现》配套源程序
遗传算法——理论、应用与软件实现》，王小平、曹立明编着 西安交通大学出版社 2002年第一版本书全面系统地介绍了遗传算法的基本理论，重点介绍了遗传算法的经典应用和国内外的新发展。全书共分11章。第1章概述了遗传算法的产生与发展、基本思想、基本操作以及应用情况；第2章介绍了基本遗传算法；第3章论述了遗传算法的数学基础；第4章分析了遗传算法的多种改进方法；第5章初步介绍了进货计算理论体系；第6章介绍了遗传算法应用于数值优化问题；第7章介绍了遗传算法应用于组合优化问题；第8章介绍了遗传算法应用于机器学习；第9章讨论了遗传算法在智能控制中的应用；第10章讨论了遗传算法与人工生命研究的相关问题；第11章介绍了遗传算法在图像处理、模式识别中的应用。-"genetic algorithm-- the theory, application and software" complementary source of genetic algorithms-- theory, Application and software, "Wang Xiaoping, Li-Ming Cao compile Xi'an Jiaotong University Press in 2002 the first book version of the comprehensive and systematic introduction of the genetic algorithm's basic On focuses on the classical genetic algorithm use and the new development. The book is divided into 11 chapters. Chapter 1 provides an overview of the genetic algorithm for the selection and development of basic ideas, basic operation and the application; Chapter 2 introduces the basic genetic algorithms; Chapter 3 of the genetic basis of a mathematical algorithm; Chapter 4 Analysis of the genetic algorithm approach to improve the variety; Chapter 5 on
Platform: |
Size: 693248 |
Author: zhoulu |
Hits:
Description: 本例研究利用Matlab工具箱的BP网络仿真某系统故障的预测,假设3个故障的样本分别为(1 1 0), (0 1 1)(1 0 1), 3个故障分别编码为(1 0), (0 1), (1 1),下面利用BP工具函数设计网络,用自适应学习率算法进行BP的设计、训练和仿真。-cases using the Matlab toolbox BP network simulation of a system fault forecast Assuming three fault samples were (1 1 0), (0 1 1) (1 0 1) three failures were coded as (1 0), (0), (1), below BP network design tool function, Adaptive learning rate BP algorithm design, simulation and training.
Platform: |
Size: 45056 |
Author: |
Hits:
Description: FIR滤波器，3个实现不同的FIR滤波器的C代码，分别包含LP、BP、HP等，具有很强的实用性-FIR filter, three different kinds of FIR filters C code, includes LP, BP, HP, with a strong practical
Platform: |
Size: 4096 |
Author: 李松 |
Hits:
Description: 这个程序是标准的BP神经网络，可以调整输入、输出和隐曾的维数。-this procedure is the standard BP neural network, can be adjusted input, output and has the implicit dimension.
Platform: |
Size: 3072 |
Author: 周润发 |
Hits:
Description: 如何用MATLAB的神经网络工具箱实现三层BP网络。仿真出一个3层的BP网络-如 ?斡肕ATLAB的神 ?网络 ???呦涫迪秩??鉈P网络 ??抡??鲆 桓 ? ?愕腂P网络
Platform: |
Size: 4096 |
Author: 劏个老鼠 |
Hits:
Description: 本文件是用C语言实现的3层BP神经网络，结构清晰，模块合理，是学习神经网络的很好的例子-This document is used C language to achieve the 3-layer BP neural networks, the structure of clear and reasonable modules, learning neural network is a good example
Platform: |
Size: 2048 |
Author: franky |
Hits:
Description: 基于BP神经网络的 参数自学习控制
（1）确定BP网络的结构，即确定输入层节点数M和隐含层节点数Q，并给出各层加权系数的初值 和 ，选定学习速率 和惯性系数 ，此时k=1；
（2）采样得到rin(k)和yout(k)，计算该时刻误差error(k)=rin(k)-yout(k)；
（3）计算神经网络NN各层神经元的输入、输出，NN输出层的输出即为PID控制器的三个可调参数 ， ， ；
（4）根据(3.34)计算PID控制器的输出u(k)；
（5）进行神经网络学习，在线调整加权系数 和 ，实现PID控制参数的自适应调整；
（6）置k=k+1，返回（1）。
-Based on the parameters of BP neural network self-learning control (1) to determine the structure of BP network, that is, determine the input layer nodes M and hidden layer nodes Q, and gives all levels of the initial value and the weighted coefficient, the selected learning rate and inertia coefficient, when k = 1 (2) sample has been rin (k) and the yout (k), calculate the moment of error error (k) = rin (k)-yout (k) (3) calculation of neural network NN all floors of the neurons in input and output, NN output layer is the output of PID controller for the three adjustable parameters,, (4) According to (3.34) Calculation of PID controller output u (k) (5) to carry out neural network learning, on-line adjustment of the weighted coefficient and, realize the adaptive PID control parameters adjust (6) purchase k = k+ 1, return (1).
Platform: |
Size: 1024 |
Author: dake |
Hits:
Description: 本程序是BP算法的演示程序, 其中的Levenberg-Marquardt算法具有实用价值.
一、网络训练
程序默认状态是样本训练状态,现将样本训练状态下的如何训练网络进行说明:
1.系统精度:
定义系统目标精度,根据需要定义网络训练误差精度.误差公式是对训练出网络的输出层节点和实际的网络输出结果求平方差的和.
最大训练次数:
默认为10000次,根据需要调整,如果到达最大训练次数网络还未能达到目标精度,程序退出.
3.步长:
默认为0.01,由于采用变步长算法,一般不需人工设置.
4.输入层数目:
人工神经网络的输入层神经元的节点数目.
5.隐含层数目:
人工神经网络的隐含层神经元的节点数目.
6.输出层数目:
人工神经网络的输出层神经元的节点数目.
7.训练算法:
强烈建议选取Levenberg-Marquardt算法,该算法经过测试比较稳定.
8.激活函数:
不同的网络激活函数表现的性能不同,可根据实际情况选择.
9.样本数据的处理:
由于程序没有实现归一化功能, 因此用来训练的样本数据首先要归一化后才能进行训练.
Platform: |
Size: 344064 |
Author: starboy_2nd |
Hits:
Description: 误差逆向传播反馈BP网络，在VC++6.0环境下编译，包括1、界面程序；2、BP神经网络训练程序；3、BP神经网络预报程序；4、BP神经网络说明程序；5、测试范例。-Reverse the spread of error feedback BP network, in VC++6.0 compiler environment, including one, the interface procedures 2, BP neural network training procedures 3, BP neural network forecasting procedures 4, BP neural networks that process 5, test sample .
Platform: |
Size: 2854912 |
Author: rsp2001 |
Hits:
Description: BP神经网络程序,C语言源代码
如下：
#include "iostream.h"
#include "iomanip.h"
#include "stdlib.h"
#include "math.h"
#include "stdio.h"
#include "time.h"
#include "fstream.h"
#define N 120 //学习样本个数
#define IN 3 //输入层神经元数目
#define HN 2 //隐层神经元数目
#define ON 2 //输出层神经元数目
#define Z 20000 //旧权值保存-》每次study的权值都保存下来
double P[IN] //单个样本输入数据
double T[ON] //单个样本教师数据
double U11[IN][HN] //输入层至第一隐层权值
double V[HN][ON] //隐层至输出层权值
double X1[HN] //第一隐层的输入
double Y[ON] //输出层的输入
double H1[HN] //第一隐层的输出
double O[ON] //输出层的输出
double YU_HN1[HN] //第一隐层的阈值
double YU_ON[ON] //输出层的阈值
double err_m[N] //第m个样本的总误差
double a //学习效率
double alpha //动量因子-BP net
Platform: |
Size: 3072 |
Author: 梅汉文 |
Hits:
Description: 采用3-6-1型bp网络学习非线性正弦信号sin(2pi*k/50),其中2*pi/50是正弦信号的频率，k是采样次数。-Bp-based 3-6-1 network used to learn non-linear sinusoidal signal sin (2pi* k/50), which is 2* pi/50 frequency sinusoidal signal, k is the sampling frequency.
Platform: |
Size: 1024 |
Author: fu_jasmine |
Hits:
Description: 应用bp算法实现对iris数据库的分类，iris数据库是人们广泛使用的用于模式分类的实例系统。它含有150个例子，分为三类，每个类由四个实数特征值描述，分别表示萼片（sepal ）长度，萼片宽度，花瓣（petal ）长度，花瓣宽度。问题是根据这四个特性值分类三种iris 植物，输入为四个特征值和类别 （5.1 3.5 1.4 0.2 0），输出算法分类结果 -Bp algorithms applied to the iris database, the classification, iris database is widely used for pattern classification of the instances of the system. It contains 150 examples, divided into three categories, each class consists of four real eigenvalue description, respectively sepals (sepal) length, sepal width, petal (petal) length, petal width. The problem is classified according to the value of these four characteristics of three kinds of iris plants, enter the four characteristic values and categories (5.1 3.5 1.4 0.2 0), the output algorithm classification results
Platform: |
Size: 3072 |
Author: 姜丽 |
Hits:
Description: 基于C开发的三个隐层神经网络,包括
1）初始化权、阈值子程序；
2）第m个学习样本输入子程序；
3）第m个样本教师信号子程序；
4）隐层各单元输入、输出值子程序；
5）输出层各单元输入、输出值子程序；
6）输出层至隐层的一般化误差子程序；
7）隐层至输入层的一般化误差子程序；
8）输出层至第三隐层的权值调整、输出层阈值调整计算子程序；
9）第三隐层至第二隐层的权值调整、第三隐层阈值调整计算子程序；
10）第二隐层至第一隐层的权值调整、第二隐层阈值调整计算子程序；
11）第一隐层至输入层的权值调整、第一隐层阈值调整计算子程序；
12）N个样本的全局误差计算子程序。
-The three development based on C hidden layer neural networks, including
1) initialization, threshold subroutines,
2) first m a learning samples input subroutines,
3) the first m a sample teachers signal subroutines,
Each unit 4) hidden layer input and output value subroutines,
Each unit 5) output layer of input and output value subroutines,
6) output layer to hidden layer of generalization error subroutines,
7) hidden layer to input layers of general error subroutines,
8) output layer to the value of the hidden layer, the output layer threshold adjustment subroutines,
9) third hidden layer to the second hidden layer, the value of the hidden layer threshold adjustment subroutines,
10) second hidden layer to the value of the hidden layer, the second hidden layer threshold adjustment subroutines,
11) first hidden layer to the input value adjustment, the first hidden layer threshold adjustment subroutines,
12) N samples of global error subroutines.
Platform: |
Size: 7168 |
Author: kison |
Hits:
Description: 利用Matlab6.5神经网络工具箱，以一组动态冲击实验数据为例建立网络模型。实验数据共有13组，将其中对曲线形状有关键性影响的10组数据作为网络的训练数据，另外3组作为测试数据用以验证网络的预测性能。-
Use Matlab6.5 Neural Network Toolbox, a dynamic impact test data, for example the establishment of the network model. Experimental data, a total of 13 groups, which have a crucial impact on the shape of the curve of 10 sets of data as the training data of the network, the other three groups as test data to verify the prediction performance of the network.
Platform: |
Size: 16384 |
Author: 陈花 |
Hits:
Description: 一个matlab编写的简单程序，显示了BP的稀疏分解，适合初学者。-A matlab simple procedure, showing the BP s sparse decomposition, is suitable for beginners.
Platform: |
Size: 3072 |
Author: 张大 |
Hits:
Description: The use of BP neural network to achieve c++ Algorithm, with detailed examples and results of analysis, as well as the effect of graph algorithms
Platform: |
Size: 504832 |
Author: 武翼客 |
Hits:
Description: 3隐层的bp神经网络，有详细的注释，各隐层的权值调整、输出层阈值调整，学习样本输出层至隐层一般化误差-3 bp neural network hidden layer, there are detailed notes, each hidden layer weight adjustment, the output layer threshold adjustment, learning sample output layer to the hidden layer generalization error
Platform: |
Size: 3072 |
Author: zhuoshi |
Hits:
Description: 现有一种合金由A,B,C三种元素及杂质组成
测试5次
A百分含量 [7.1 7.0 6.9 6.8 7.2]
B百分含量 [3.2 3.4 3.6 3.8 4.0]
C百分含量 [2.5 2.9 3.1 2.6 2.2]
硬度[78 65 78 69 72]
用BP神经网络进行拟合BP神经网络进行拟合-The BP neural network to carry on the fitting
Platform: |
Size: 9216 |
Author: 陈晗 |
Hits:
Description: 用C语言编写的BP神经网络算法，能够实现6输入3输出的神经网络-BP neural network algorithm written in C, it is possible to achieve 3 6 input output neural network
Platform: |
Size: 3072 |
Author: 石伟 |
Hits: