16 datasets found

The MNIST dataset is a large dataset of handwritten digits, and the Caltech101 Silhouettes dataset is a dataset of binary silhouettes of objects.

The MNIST dataset is a large dataset of handwritten digits, and the Temporal MNIST dataset is a variant of MNIST where similar inputs are put together.

The MNIST dataset is a collection of images of handwritten digits, with size n = 70,000 and D = 784.

The mini-MNIST dataset is a smaller version of the MNIST dataset, containing 10,000 28x28 grayscale images of handwritten digits.

The MNIST dataset is a dataset of handwritten digits.

notMNIST is a dataset of 60,000 28x28 grayscale images in 10 classes, with 6,000 images per class.

The EMNIST dataset contains 372,450 samples of the 26 letters A-Z (labels), each represented in a 28 × 28 dimension.

The eBioDigitDB database comprises on-line handwritten digits from 0 to 9 acquired using 93 total subjects.

MNIST dataset consists of 60,000 training and 10,000 testing samples, while SVHN consists of 73,257 training and 26,032 testing digital images.

The USPS dataset consists of 9298 images of handwritten digits 0-9 (10 classes) of 16x16 pixels in gray scale.

The MNIST dataset is a collection of 70,000 28x28 grayscale images of handwritten digits, and the USPS dataset is a collection of 9,298 16x16 grayscale images of handwritten...

The OCR dataset is a dataset of handwritten digits, each image is an 8x16 binary image, and there are 52152 samples in total.

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 Scaled and Translated Image Recognition (STIR) dataset contains four different tasks, which classify emojis, handwritten digits, traffic signs and aerial scenes, respectively.

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...