MNIST Dataset

doi:doi:10.57702/6w0eiklj

MNIST Dataset

The MNIST dataset (Lecun et al., 1998), which consists of 60,000 gray-scale images of handwritten digits. Each image has an accompanying label in {0, 1,..., 9}, and is stored as a 28 × 28 matrix that takes on values in [0, 255]. We first divide the entries of all the images by 255. Next, since there is no variation in the peripheral pixels of the images (Gallaugher & McNicholas, 2018), which violates model (1), we add an independent perturbation N (0, 0.01) to each element of the image. Finally, we vectorize each image to obtain a vector xi ∈ R784.

BibTex:

@dataset{Yann_LeCun_and_L´eon_Bottou_and_Yoshua_Bengio_and_Patrick_Haffner_2024,
    abstract = {The MNIST dataset (Lecun et al., 1998), which consists of 60,000 gray-scale images of handwritten digits. Each image has an accompanying label in {0, 1,..., 9}, and is stored as a 28 × 28 matrix that takes on values in [0, 255]. We first divide the entries of all the images by 255. Next, since there is no variation in the peripheral pixels of the images (Gallaugher & McNicholas, 2018), which violates model (1), we add an independent perturbation N (0, 0.01) to each element of the image. Finally, we vectorize each image to obtain a vector xi ∈ R784.},
    author = {Yann LeCun and L´eon Bottou and Yoshua Bengio and Patrick Haffner},
    doi = {10.57702/6w0eiklj},
    institution = {No Organization},
    keyword = {'28x28 images', 'Binary Images', 'Classification', 'Dataset', 'Deep Learning', 'Digit Recognition', 'Feature Alignment', 'Gray Scale Images', 'Handwriting Digits', 'Handwritten Digit Images', 'Handwritten Digit Recognition', 'Handwritten Digits', 'Handwritten digits', 'Image Classification', 'Image Clustering', 'Image Inputs', 'Image Recognition', 'Image classification', 'Labels', 'MNIST', 'MNIST Dataset', 'Machine Learning', 'Pattern Recognition', 'Recognition', 'Training Dataset', 'Unsupervised Learning', 'anomaly detection', 'convolutional neural networks', 'digits', 'gray-scale images', 'grayscale', 'handwritten digit recognition', 'handwritten digits', 'image classification', 'image recognition', 'images', 'occlusion', 'rotation'},
    month = {nov},
    publisher = {TIB},
    title = {MNIST Dataset},
    url = {https://service.tib.eu/ldmservice/dataset/mnist-dataset},
    year = {2024}
}