IRJET - Study on the Effects of Increase in the Depth of the Feature Extractor for Recognizing Hand Written Digits in Convolutional Neural Network

This document discusses a study on the effects of increasing the depth of the feature extractor for recognizing handwritten digits in a convolutional neural network (CNN). Specifically, it analyzes the performance of a CNN model on the Modified National Institute of Standards and Technology (MNIST) dataset with variations in the number of filters used in deeper layers of the proposed model. The study finds that increasing the number of filters in the convolutional layers improves the accuracy of the model for classifying handwritten digits.