搜索资源列表
nnforcast
- 本程序根据训练好的网络文件ANN.mat预测新的数据文件，得到均方误差，并画出预测数据和原数据的对比图。此程序运用到了很多Matlab编程中常用到的表达方式，还有一些神经网络编程的基本概念的表达，如归一化的表达。希望能对别人有所帮助.-the procedures under the trained network file ANN.mat anticipating new data files, to be mean-square error. and the mapping out of t
Dominantset
- 一种 较新的聚类算法 Dominant-set 的代码，包括聚类算法的代码和测试代码。该算法最大特点 就是基于图理论的 ，相对于Normalized Cut,计算复杂度低很多，况且能自动决定类的个数
gacode-in-c
- This a GA implementation using binary and real coded variables. Mixed variables can be used. Constraints can also be handled. All constraints must be greater-than-equal-to type (g >= 0) and normalized (see the sample problem in prob1 in objective(
guiyihua.rar
- mtlab神经网络数据归一化源代码，在实际处理数据时很有用，希望大家能够分享~,mtlab neural network data normalized source code, when in the actual processing of data was very useful, hope that we can share ~
BP
- BP神经网络故障检测，适合初学者看。包括归一化、反归一化处理，文件保存等功能。-BP neural network fault detection, suitable for beginners to see. Including normalization, anti-normalized, save the file and other functions.
datainit
- 神经网络训练样本归一化程序，并能均匀的分离训练样本和检验样本-Neural network training samples normalized procedures, and uniform separation of training samples and testing samples
ANN
- bp神经网络对短期电力负荷的预测，一周预测一天，输入是归一过的数据。-bp neural network for short-term load forecast, the forecast one day a week, enter the data have been normalized.
bp_v1_2
- -----引入动量的算法 建立一个3层（含输入层）的BP神经网络，并对其进行训练 输入层不进行数据处理，隐含层激活函数为sigmod函数，输出层为线性函数 输入输出数据归一化到[-1,1]，数据在矩阵中按行向量表示 即x=[x11,x12 x21,x22 ... xp1,xp2] y=[y1 y2 ... yp] p为样本数 -The introduction of the algorithm ----- momentum to build a three-layer (
123
- 关于神经网络归一化方法的整理 由于采集的各数据单位不一致，因而须对数据进行[-1，1]归一化处理，归一化方法主要有如下几种，供大家参考：-Naturalization on the neural network method of finishing a collection of various data unit due to inconsistencies, which will require the data [1,1] normalized, normalized severa
bpprogramming
- 这个程序根据训练好的网络文件ANN.mat预测新的数据文件，得到均方误差，并画出预测数据和原数据的对比图。此程序运用到了很多Matlab编程中常用到的表达方式，还有一些神经网络编程的基本概念的表达，如归一化的表达。希望能对大家有所帮助-This program the trained network file ANN.mat predict new data file, get the mean square error, and forecast data and the original d
nntrain
- 通过对数据进行归一化处理，进行神经网络的训练，并最终的到满意的结果-Normalized by the data processing, the neural network training, and the final results to the satisfaction
FastNormalizedCross-Correlation
- 这是一篇论文，主要内容是归一化互相关算法的原理及快速计算-Fast Normalized Cross-Correlation
Clustering-src
- normalized cut clusterin algorithm.
EvaluateMetric
- Clustering Evaluation: Evaluate the clustering result by accuracy and normalized mutual information Deng Cai, Xiaofei He, and Jiawei Han, "Document Clustering Using Locality Preserving Indexing", in IEEE TKDE, 2005. Bibtex source bestMap hun
mapminmax_boiler
- 对于较低版本的matlab库中，缺少归一化的函数mapminmax.m 包含（它的子函数boiler_process.m），它是libsvm-mat需要用到的函数。-With earlier versions of matlab library, the lack of normalized functions mapminmax.m contains (its Functions boiler_process.m), it is libsvm-mat need to use the funct
pzernike_recognition
- 以BP算法和RRA理论为基础，采用BP_RRA作为人脸识别分类器，结合归一化伪zernike矩，提出一种基于归一化伪zernike矩和BP_RRA神经网络的人脸识别算法。-BP algorithm and the RRA theory, based on the normalized pseudo-zernike moments BP_RRA as face recognition classifier combined to propose a face recognition algorit
LSSVM
- 通过运用LSSVM的方来来进行sine函数的归一化处理-Through the use of LSSVM square to the sine function normalized
knn
- k近邻分类器分类 包括PCA功能 归一化 并且带有交叉检验功能-k nearest neighbor classifiers including PCA function normalized and with cross-validation function
ELSA_v0.1.tgz
- This package contains the code for the Enhanced Local Subspace Affinity (ELSA) with Enhanced Model Selection (EMS+) and number of motions estimation based on the eigenvalue spectrum of the Symmetric Normalized Laplacian matrix.-This package co
Normalized-cuts
- Normalized cuts and image segmentation