Colorectal Histology CSV Multi-classification Accuracy Comparison using Various Machine Learning Models

The MNIST database was derived from a larger dataset known as the NIST Special Database. In this paper, colorectal histology CSV data is multi-classified with several method: Convolutional Neural Network (CNN), K-Nearest Neighbour (KNN), Logistic Regression, and Random Forest. The aim of this paper is to compare the performance of each method and define the optimum algorithm; the best method is obtained with CNN with 82.2% accuracy.