18 datasets found

The US Postal Service (USPS) dataset is a collection of 9298 handwritten digits automatically scanned from envelopes by the US Postal Service.

The dataset used in the paper is the Pen-Based Recognition of Handwritten Digits dataset.

The MNIST dataset is a large collection of handwritten digit images.

The dataset used in this paper is the handwritten digits dataset.

The LeNet-5 dataset is a large collection of handwritten digit images.

The F-MNIST dataset is a dataset of handwritten digits.

The P-MNIST is a dataset containing 10 tasks where the first task is the MNIST dataset.

Handwritten digit dataset

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

The dataset used in the paper is LeNet, a convolutional neural network for image classification.

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

A dataset of 70000 handwritten samples of Bengali numerals for recognition using artificial neural network based architecture pre-trained by a stacked denoising autoencoder.

Binary images are simple — two possible pixel-valued signals with a single channel. The simplicity of binary images has a significant advantage compared to colored and gray...

The MNIST handwritten digit database is a dataset of 60,000 8x8 grayscale images 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 dataset used in the paper is MNIST variations, which consists of gray scale handwritten digits of size 28x28 with controlled factors of variations such as background noise,...

The MNIST-SVHN-Text dataset is a multi-modal dataset consisting of images, text, and labels.

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...