In this issue, “Best of the Web” presents the modified National Institute of Standards and Technology (MNIST) resources, consisting of a collection of handwritten digit images used extensively in optical character recognition and machine learning research.

Cited by 4,455

Comparison of kNN Classifier and Simple Neural Network in Handwritten Digit Recognition Using MNIST Database

Wiktoria Koman, Kuba Małecki · Communications in computer and information science · 2024

Cited by 0

AN INTELLIGENT ROLLING BEARING FAULT DIAGNOSIS METHOD OF CNN BASED ON MNIST DATABASE OF HANDWRITTEN DIGITS

Kai Wen1, Maohua Xiao, Cunyi Zhang et al. · International Journal of Mechatronics and Applied Mechanics · 2019

An intelligent rolling bearing fault diagnosis method of convolutional neural network (CNN) based on MNIST database of handwritten digits was proposed. The equal length interception of the vibration signal of the rolling bearing was performed, and the intercepted signal was reconstructed into two-dimensional pictures in sequence. In order to ensure the authentic and effective restoration of the fault characteristics of the vibration signal, no preprocessing was performed on the vibration signal, and direct interception was performed to reconstruct the twodimensional pictures. To realize intelligent fault diagnosis of rolling bearings, the failure pictures were input as feature maps, and a CNN classifier model based on MNIST database of handwritten digits was established. In order to verify the validity of the rolling bearing fault diagnosis method proposed in this paper, the open-end rolling bearing data from Case Western Reserve University and the rolling bearing data collected under laboratory conditions were experimentally verified respectively. The experimental results were then compared with the traditional BP neural network, BP neural network optimized by particle swarm optimization, wavelet energy entropy support vector machine optimized by particle swarm optimization, support vector machine based on variational mode decomposition mutual approximation entropy and BP neural network optimized by genetic algorithm on the effectiveness of fault pattern recognition. The results show that this method can identify effectively the fault type of the rolling bearing, and the diagnosis efficiency is higher. The method has strong feature extraction and recognition capabilities.

Cited by 1Open access

EMNIST: Extending MNIST to handwritten letters

Gregory Cohen, Saeed Afshar, Jonathan Tapson et al. · 2017

The MNIST dataset has become a standard benchmark for learning, classification and computer vision systems. Contributing to its widespread adoption are the understandable and intuitive nature of the task, the relatively small size and storage requirements and the accessibility and ease-of-use of the database itself. The MNIST database was derived from a larger dataset known as the NIST Special Database 19 which contains digits, uppercase and lowercase handwritten letters. This paper introduces a variant of the full NIST dataset, which we have called Extended MNIST (EMNIST), which follows the same conversion paradigm used to create the MNIST dataset. The result is a dataset that constitutes a more challenging classification task involving letters and digits, and one that shares the same image structure and parameters as the original MNIST task, allowing for direct compatibility with all existing classifiers and systems. Benchmark results using an online ELM algorithm are presented along with a validation of the conversion process through the comparison of the classification results on NIST digits and the MNIST digits.

Cited by 1,531

Layers Graphene-hBN Dataset

E. Mariño Hernández, Pedro Palomares-Baez, José Manuel Nápoles-Duarte · Figshare · 2023

<pre>Dataset of the Graphene-MNIST system: Contains 60,000 graphene layers doped with B-N with the projections of the digits from 0 to 9 from the MNIST database.</pre>

Cited by 0Open access

Layers Graphene-hBN Dataset

Hernandez, Esther, Palomares-Baez, Pedro, Nápoles-Duarte, José Manuel · Figshare · 2023

<pre>Dataset of the Graphene-MNIST system: Contains 60,000 graphene layers doped with B-N with the projections of the digits from 0 to 9 from the MNIST database.</pre>

Cited by 0Open access

Parameter selection for DGRL on validation set with respect to different values of and on the (a) Extended YaleB database (# Tr = 15), (b)CUReT database (# Tr = 25), (c) COIL-100 database (# Tr = 25), and (d) MNIST database (# Tr = 30), respectively.

Jinshan Qi (5180714), Rui Xu (158313) · Figshare · 2025

Parameter selection for DGRL on validation set with respect to different values of and on the (a) Extended YaleB database (# Tr = 15), (b)CUReT database (# Tr = 25), (c) COIL-100 database (# Tr = 25), and (d) MNIST database (# Tr = 30), respectively.

Cited by 0Open access

Parameter selection for KDGRL on validation set with respect to different values of and on the (a) Extended YaleB database (# Tr = 15), (b)CUReT database (# Tr = 25), (c) COIL-100 database (# Tr = 25), and (d) MNIST database (# Tr = 30), respectively.

Jinshan Qi (5180714), Rui Xu (158313) · Figshare · 2025

Parameter selection for KDGRL on validation set with respect to different values of and on the (a) Extended YaleB database (# Tr = 15), (b)CUReT database (# Tr = 25), (c) COIL-100 database (# Tr = 25), and (d) MNIST database (# Tr = 30), respectively.

Cited by 0Open access

Retraction Notice: MNIST Handwritten Digit Recognition using Machine Learning

Elizabeth Rani. G, M Sakthimohan, Abhigna Reddy. G et al. · 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · 2022

Identification of the MNIST database that will be in handwritten digit can be recognized by the machine. It can be recognized that the human handwritten form into the machine language. Here we are using some machine learning algorithm that is Convolutional Neural Network (CNN). MNIST database consist of nine digits that is 0 to 9. It can be used to change over manually written digits into machine lucid arrangements. The primary target of this work is to guarantee successful and dependable methodologies for acknowledgment of written by hand digits and make banking tasks more straightforward and mistake free. The MNIST database will be identified by the machine very accurately. Here we are finding the handwritten digit accuracy.

Cited by 1

Analytical Calculation of Weights Convolutional Neural Network

P. Sh. Geidarov · Optical Memory and Neural Networks · 2024

In this paper proposes an algorithm for the analytical calculation of convolutional neural networks without using neural network training algorithms. A description of the algorithm is given, on the basis of which the weights and threshold values of a convolutional neural network are analytically calculated. In this case, to calculate the parameters of the convolutional neural network, only 10 selected samples were used from the MNIST digit database, each of which is an image of one of the recognizable classes of digits from 0 to 9, and was randomly selected from the MNIST digit database. As a result of the operation of this algorithm, the number of channels of the convolutional neural network layers is also determined analytically. Based on the proposed algorithm, a software module was implemented in the Builder environment C++, on the basis of which a number of experiments were carried out with recognition of the MNIST database. The results of the experiments described in the work showed that the computation time of convolutional neural networks is very short and amounts to fractions of a second or a minute. Analytically computed convolutional neural networks were tested on the MNIST digit database, consisting of 1000 images of handwritten digits. The experimental results showed that already using only 10 selected images from the MNIST database, analytically calculated convolutional neural networks are able to recognize more than half of the images of the MNIST database, without application of neural network training algorithms. In general, the study showed that artificial neural networks, and in particular convolutional neural networks, are capable of not only being trained by learning algorithms, but also recognizing images almost instantly, without the use of learning algorithms using preliminary analytical calculation of the values of the neural network’s weights.

Cited by 1

HANDWRITTEN DIGITS CLASSIFICATION BASED ON DISCRETE WAVELET TRANSFORM AND SPIKE NEURAL NETWORK

Dina A. ABDULQADER, Marwa T. NASER · 2022

In this paper, a handwritten digit classification system is proposed based on the Discrete Wavelet Transform and Spike Neural Network. The system consists of three stages. The first stage is for preprocessing the data and the second stage is for feature extraction, which is based on Discrete Wavelet Transform (DWT). The third stage is for classification and is based on a Spiking Neural Network (SNN). To evaluate the system, two standard databases are used: the MADBase database and the MNIST database. The proposed system achieved a high classification accuracy rate with 99.1% for the MADBase database and 99.9% for the MNIST database.

Cited by 0Open access

MNIST and SVHN Digit Classification

S. Chandrakala, M. Ghani, B S Sanath et al. · International Journal of Science and Research Archive · 2025

By utilising the MNIST database coupled with the SVHN data, identification of multiple handwritten digits is being achieved by the model built. In this particular use case, Convolutional neural networks (CNN) algorithm is integrated with the MNIST dataset, whereas Long short-term memory (LSTM) is employed for the SVHN dataset to sequentially classify the digits. Furthermore, the concatenation of both outputs will be trained using a final classifier. The MNIST database contains numbers ranging from 0-9, while the other database is similar in flavour, containing over 60,000 labelled images. The primary goal of this project is to develop a reliable, effective, and efficient methodology for recognizing and identifying multiple handwritten digits with minimum errors. The applications of such an accurate model lies in banking sectors, healthcare departments and many more.

Cited by 0Open access