搜索资源列表
bolztmann
- 使用bolztmann机实现多层分类网络，内有mnist数据集-Machine to achieve multiple classifiers using bolztmann network data sets within mnist
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
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 s
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
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
CNN-MINIST
- 利用卷积神经网络进行MINIST数据集的分类识别，MATLAB源程序。-Convolution neural network classification MNIST dataset, MATLAB source.
Softmax_exercise
- Softmax用于多分类问题，本例是将MNIST手写数字数据库中的数据0-9十个数字进行分类，其中训练样本有6万个，测试样本有1万个数字是0~9-Softmax for multi classification problems, the present case is the handwritten data MNIST digital 0-9, classification, training samples which have
MNIST_classify
- 使用决策树，支持向量机以及人工神经网络完成对MNIST手写数字体的分类。-Using a decision tree, support vector machines and artificial neural network to classify the number of MNIST handwritten font.
神经网络mnist
- 利用神经网络对手写识别系统进行分类，正确率高达92%。(Using neural network to classify handwritten recognition system, the correct rate is as high as 92%.)
fisher
- 利用fisher方法实现手写体数字多分类识别，采用mnist数据集(simple program using fisher)
mnist实验
- 包含训练用的图片数据包，python源代码，mnist实验，深度学习，进行图片分类(mnist experiment.python code.deep learning.picture classification,etc.)
MNLIST and CNN
- 实现了在Mnist上的分类，使用了卷积神经网络(use convoluntional neural network to implement classificaiton on Minist.)
mnist
- 利用keras实现手写数字识别，使用CNN模型 全连接层+两个卷积层，最后Softmax分类器，识别率超过96%(Using keras to realize handwritten numeral recognition baesd on CNN model. One whole connection layer + two convolution layers, and a Softmax classifier. The re
mnist_test_opencv
- 利用opencv的ML-SVM，进行·mnist数据集的训练分类。 同时包含该数据集的读取(use opencv's ML-SVM to carry out training classification of MNIST dataset. Including the reading of the data set)
dbn_tf-master
- 利用深度置信网络实现对mnist数据集的分类(sort out the set of mnist with DBN)
mnist
- 使用了全连接网络，卷积神经网络，循环神经网络分别构建不同的分类器，如何通过模型保存原理进行保存。(Using the fully connected network and convolution neural network, recurrent neural network builds different classifiers respectively, and how to save them through the pres
mnist分类
- mnist分类，python，tensorflow，深层神经网络(MNIST classification, python, tensorflow, deep neural network)
tensorflow
- 利用tensorflow对mnist数据集进行分类(classify the mnist dataset by tensorflow)
bp_mnist
- matlab写的bp神经网络对mnist数据集进行学习分类(Learning and classification of MNIST data sets based on BP neural network written by MATLAB)
PCA+mnist
- 基于python，利用主成分分析（PCA）和K近邻算法（KNN）在MNIST手写数据集上进行了分类。 经过PCA降维，最终的KNN在100维的特征空间实现了超过97%的分类精度。(Based on python, it uses principal component analysis (PCA) and K nearest neighbor algorithm (KNN) to classify on the MNIST handwr