Classification of Handwritten Digits using Machine Learning Techniques

Prashasti Gupta, Navni Bhatia

The MNIST dataset (Mixed National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems. ^[1][2] The database is also widely used for training and testing in the field of machine learning. The MNIST database contains 60,000 training images and 10,000 testing images. ^[3]

In this paper, we aim to apply classification techniques to predict labels for records in the MNIST dataset using machine learning. In total, there are 10 labels ranging from 0-9. Classification will be done using Random Forest Classification Algorithm. We also aim to implement Principle Component Analysis to reduce the dimensionality of the data while retaining its variance. To this data, we aim to apply K Nearest Neighbors Classification Algorithm