Please use this identifier to cite or link to this item:
http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/9983
Title: | MNIST Digit Classification using Machine Learning |
Authors: | Khandelwal, Hridyesh Kumar, Pardeep [Guided by] |
Keywords: | Handwritten digit classification K-nearest neighbor |
Issue Date: | 2023 |
Publisher: | Jaypee University of Information Technology, Solan, H.P. |
Abstract: | This project intends to carry out the task of handwritten digit classification. The task will be carried out using various Machine-Learning and Deep-Learning algorithms. The project will be implemented using python. With the help of Machine-Learning and Deep-Learning algorithms, we will be able to build models which will take an image of a human handwritten digit as input, and will be able to classify those digits into categories (0-9). We will then analyze which algorithms are relatively more accurate and why. We will use the following algorithms: KNN (K-Nearest Neighbor), Decision Trees(DT), Random -Forests(RF), Artificial Neural Networks (ANN) and Convolutional-Neural-Networks(CNN). We will use a dataset called MNIST. In this dataset we will implement the algorithms listed above. After that we will find the accuracy of all methods, and rank them accordingly. Then we will attempt to understand why some algorithms are less accurate than others. |
Description: | Enrollment No. 191312 |
URI: | http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/9983 |
Appears in Collections: | B.Tech. Project Reports |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
MNIST Digit Classification using Machine Learning.pdf | 2.43 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.