• Sankar K
• Dr.Priya.M

This paper presents an implementation using Convolutional Neural Network to achieve the classification of the MNIST handwritten digit database. Here, we use plot of loss during training and classification accuracy to determine the performance of the neural network. The experimental results show that to a certain extent, the neural network can be used to solve classification problem. The thing of our work is going to be to make a model which will be ready to identify and determine the handwritten number from its image with better delicacy. We aim to finish this by using the generalities of Convolution Neural Network and MNIST dataset. However, the accuracy rate cannot be guaranteed and potential reasons are discussed. Then we try to modify the structure of the original neural network into a Convolutional Neural Network (CNN). The results indicate that CNN can be used to improve the performance during solving image recognition problem. At last, the results generated by our network system the most objective of this paper is to make sure effective and dependable approaches for recognition of handwritten integers.

MNIST handwritten digit database, Convolutional Neural Network, Deep learning

"MNIST DIGIT REPRESENTATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 4, page no.l163-l166, April-2023, Available :http://www.jetir.org/papers/JETIR2304B28.pdf

"MNIST DIGIT REPRESENTATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 4, page no. ppl163-l166, April-2023, Available at : http://www.jetir.org/papers/JETIR2304B28.pdf