Menu

Topological Data Analysis of MNIST Dataset

A novel approach to machine learning tasks on grayscale images is explored and implemented by integrating Topological Data Analysis (TDA). The method applies persistent homology to generate a wide array of topological features from a point cloud derived from the image, using grayscale filtration and various filtrations defined on the binarized image. The effectiveness of this pipeline is demonstrated as a significant dimensionality reduction tool on the MNIST digits dataset, achieving similar accuracy in digit image classification.

Keywords: Homology,Simplicial complex,Data Filtration ,Persistent Diagram,MNIST dataset , Machine learning,Topological data Analysis
Tools: Python,SciPy,Ripser,Numpy,Gudhi,TensorFlow
Department: Department of Mathematics

Project Team Members

Name Email
Waseem Abbas waseem2020@namal.edu.pk
Shahid Hussain shahid2020@namal.edu.pk

Project Poster

Related Projects

Career Development Center

Our primary goal is to empower students by providing guidance for internships, experiential education, full-time employment, and higher education choices based on current job market trends.

Important Links

Get In Touch

Address: 30 km Talagang Road, Mianwali, 42250, Pakistan.

Phone: +92 (0) 459-236995 Ext. 101, 107

WhatsApp:+92 300 9236995

Email: info@namal.edu.pk

Copyrights © 2024. Namal University Mianwali. All Rights Reserved.