2026-10-14T20:37:52Z https://www.scidb.cn/oai

10.57760/sciencedb.34922 2026-01-06T10:09:01Z

2026-01-06 MNIST 手写数字识别基准数据集和光学网络训练代码 doi:10.57760/sciencedb.34922 en The MNIST database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems. It contains 60,000 training images and 10,000 testing images. Each image is a $28 \times 28$ pixel grayscale image of a handwritten digit from 0 to 9. It is considered the "Hello World" of machine learning and is a standard benchmark for evaluating learning algorithms and neural network architectures. Handwritten Digits; Image Recognition; Computer Vision; Machine Learning Benchmark; Character Recognition Haiqi Gao RESTRICTED dataset http://www.doi.org/10.1021/acsphotonics.4c01342 Science Data Bank