30 datasets found

The AffNIST dataset is a large collection of images of handwritten digits with affine transformations.

We use the preprocessed binarized MNIST dataset from [49] which has a split of 50k/10k/10k.

The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions.

The MNIST handwritten digit database is a dataset of 60,000 8x8 grayscale images of handwritten digits.

The TiCC dataset is a dataset of handwritten digits.

The ICDAR dataset is a dataset of handwritten digits.

The MNIST dataset consists of 60,000 training samples and 10,000 test samples. Each sample is a 28×28 pixel grayscale handwritten digital image.

The MNIST database of handwritten digits is a popular benchmark data set for classification algorithms.

The Pendigits, UJIpenchars and Assamese datasets are small datasets of handwritten digits.

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...