The MNIST database (Mixed National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems.[1][2] The database is also widely used for training and testing in the field of machine learning.[3][4] It was created by "re-mixing" the samples from NIST's original datasets. The creators felt that since NIST's training dataset was taken from American Census Bureau employees, while the testing dataset was taken from American high school students, it was not well-suited for machine learning experiments.[5] Furthermore, the black and white images from NIST were normalized to fit into a 20x20 pixel bounding box and anti-aliased, which introduced grayscale levels.[5]

The MNIST database contains 60,000 training images and 10,000 testing images.[6] Half of the training set and half of the test set were taken from NIST's training dataset, while the other half of the training set and the other half of the test set were taken from NIST's testing dataset.[7] There have been a number of scientific papers on attempts to achieve the lowest error rate; one paper, using a hierarchical system of convolutional neural networks, manages to get an error rate on the MNIST database of 0.23 percent.[8] The original creators of the database keep a list of some of the methods tested on it.[5] In their original paper, they use a support vector machine to get an error rate of 0.8 percent.[9]

1. C++标准模板库从入门到精通 


3. 跟老菜鸟学python

4. 在VC2015里学会使用tinyxml库

5. 在Windows下SVN的版本管理与实战

6.Visual Studio 2015开发C++程序的基本使用



©️2020 CSDN 皮肤主题: 大白 设计师: CSDN官方博客 返回首页
钱包余额 0