MNIST database

[7] Furthermore, the black and white images from NIST were normalized to fit into a 28x28 pixel bounding box and anti-aliased, which introduced grayscale levels.

SD-3 was the training set, and it contained digits written by 2000 employees of the United States Census Bureau.

[7] It was found that machine learning systems trained and validated on SD-3 suffered significant drops in performance on the test set.

Each was size-normalized to fit in a 20x20 pixel box while preserving their aspect ratio, and anti-aliased to grayscale.

[20] The highest error rate listed[7] on the original website of the database is 12 percent, which is achieved using a simple linear classifier with no preprocessing.

[22] In 2011, an error rate of 0.27 percent, improving on the previous best result, was reported by researchers using a similar system of neural networks.

[23] In 2013, an approach based on regularization of neural networks using DropConnect has been claimed to achieve a 0.21 percent error rate.

[25][26] Also, the Parallel Computing Center (Khmelnytskyi, Ukraine) obtained an ensemble of only 5 convolutional neural networks which performs on MNIST at 0.21 percent error rate.