搜索资源列表
train-images-idx3-ubyte
- MNIST数据集中图像数据文件， 60000个训练集-The MNIST dataset image data files, 60000 training set
Database-digit-handwritten
- 手写体数字识别的训练数据库（MNIST）。 收集了500多位实验者的共60000个样本。-THE MNIST DATABASE of handwritten digits Four files are available on this site: train-images-idx3-ubyte.gz: training set images (9912422 bytes) train-labels-idx1-ubyte.gz: training set label
Demo-MNist
- neural network about hand write dgr-neural network about hand write dgree
123MNISTTrain
- 手写数字训练识别，基于MNIST库进行训练识别，6W个训练样本，识别率95 以上-Handwritten numeral recognition training, training on MNIST library identification, 6W training samples, the recognition rate of 95 or more
c_code_dbn
- 这是深度置信网的C++版本。 rbm.h 实现自动编码. mnist.h 读取MNIST数据文件 spectrum.inl RGBs与颜色的映射 demo.cc 训练/测试主程序-The deep learning algorithm is based on the matlab code provided by Geoff Hinton etc at http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html
main
- 利用opencv识别手写数字的分类，并识别，利用了mnist数据库-Using opencv recognize handwritten digits classification and identification, the use of mnist database
myBP
- 采用典型的BP算法实现了基于MNIST的手写数字识别采用输入层、隐含层和输出层的三层结构，实现了BP算法下的神经网络。用7000个样本进行自洽检验，正确率99.79 。-Using typical BP algorithm based on MNIST handwritten numeral recognition using input layer, hidden layer and output layer, three-layer structure, to achieve the neu
DeepNeuralNetwork20131115
- It provides deep learning tools of deep belief networks (DBNs).-Run testDNN to try! Each function includes descr iption. Please check it! It provides deep learning tools of deep belief networks (DBNs) of stacked restricted Boltzmann machines (RB
深度神经网络
- It provides deep learning tools of deep belief networks (DBNs).-Run testDNN to try! Each function includes descr iption. Please check it! It provides deep learning tools of deep belief networks (DBNs) of stacked restricted Boltzmann machines (RBMs).
Release
- 闲时无聊，搭了一个基于深度神经网络的手写数字识别系统。该系统在手写数字数据库mnist测试达到了99.22 的准确率。整个系统基于C++开发，可以很方便的移植到其他平台。 其中手写数字数据库mnist（http://yann.lecun.com/exdb/mnist/），有60000个训练样本数据集和10000个测试用例。它是由Google实验室的Corinna Cortes和纽约大学柯朗研究所的Yann LeCun建立的一个手写数字数据库。同时它是nist数据库的一个子集。
Handwritten-Character
- 基于CNNs的手写字符识别系统，载入MNIST手写字符数据库，通过训练提取特征，达到99 的识别率-Based on CNNs handwritten character recognition system, load MNIST handwritten character database, extract features through training, up to 99 recognition rate
SvmMNIST
- 通过SVM算法识别MNIST手写数字库，并加入了一些预处理算法，包括数字图像的大小调整归一化等，效果不错。-By SVM algorithm identifies MNIST handwritten digital library and added some preprocessing algorithms, including the size of the digital image adjustment normalized so good results.
readMNIST
- mnist原图尺寸读取， 灰度图尺寸为28*28-mnist original scale image reading with scale of 28*28
MNIST
- 这个压缩包，是一个手写数字识别库，世界上最权威的，美国邮政系统开发的，可以作为标准的数据集合使用测试分类器-This compression package, is a handwritten numeral recognition , the world' s most authoritative, the U.S. postal system developed can be used as a standard data set using the test classifier
test
- python实现用逻辑回归识别和分类人工手写数字-Classifying MNIST digits using Logistic Regression
CUDA-CNN-master
- CNN cuda的加速。 start-of-art结果的流行的数据集 1。测试mnist并获得99.76 ,投票后(99.82 )(最好的99.79 ) 2。测试cifar-10并获得81.42 最好(90 ) 3。测试cifar - 100和51.13 (最好的65 )-CNN accelerated by cuda. The start-of-art result s of popular datasets 1. Test on mnist and get 99.76
hw4
- k近邻分类，内部有文档详细说明，具体例子是通过k近邻对常用数据集mnist.mat（头像数据）进行分类-k nearest
CUDA-CNN-master
- 提升mnist字符识别准确度，利用cuda进行加速其识别过程-improve the accuracy of mnist
MNIST_theano
- 利用theano库完成MNIST手写识别，包括稀疏自编码机，多层感知机，卷积神经网络-using the theano to complete the handwriting congnization in MNIST ,include Denoising AutoEncoder,MLP,Convolution Neutral Network.
CNNfor-handwriting-Mnist
- 能够实现对手写字符的识别，是一个简单的系统，功能齐全-To achieve recognition of handwritten characters, it is a simple system, fully functional