Digit Recognition using the Artificial Neural Network

Abstract

Digit recognition using the Artificial Neural Network method is discussed in this study. Due to the enormous volumes of data and algorithms, the neural network can now be used to train the network and get the desired result. With the advancement in information and communication technology, internet access has increased as the use of technology increases the demand for digit recognition systems has gained popularity. This paper will discuss one of the techniques for digit recognition. We will train our model with the MNIST dataset & then test our model. Programming in Python is used to perform digit recognition. We have taken a dataset of 28,000-digit images, that will be used for training and 14,000-digit images for testing. The test performance accuracy of our multi-layer artificial neural network is 99.59 %.