Badri Adhikari
Associate Professor
Department of Computer Science, University of Missouri-St. Louis
Founder of Process Feedback
Email: adhikarib@umsl.edu
TL;DR: My research interests are Explainable AI, Health Informatics, Bioinformatics, and AI in Education.
I am an Associate Professor in the Department of Computer Science at the University of Missouri-St. Louis. Before joining in 2017, I obtained my PhD from the University of Missouri-Columbia. My academic background is grounded in deep learning. A method I developed for predicting protein contacts, named DNCON2, was state-of-the-art when it was published in 2017. It was among the very first methods based on convolutional deep neural networks. A few years later, my research was funded by NVIDIA, Google, and the U.S. National Science Foundation. Within AI, I have become interested in explainable AI, a subfield that aims to explain why AI works or fails. I call this the pursuit of “understanding the logic behind the magic of AI.” More recently, I have also developed an interest in AI usage in health informatics and education. In 2023, I developed a new online educational tool for students, Process Feedback. Relevant in this AI era, it is unique in that it promotes self-reflection, metacognition, and academic integrity in students in a novel way. The tool was also featured by UMSL Daily and Missouri Online. Currently, I am engaged in all four areas of my research interests—explainable AI, health informatics, bioinformatics, and AI in education. A major inspiration for my work has been Richard Hamming’s talk “You and Your Research.”
Online profiles: Google scholar, LinkedIn, ORCID, UMSL, Github.
Mailing address:
1 University Blvd. 312 Express Scripts Hall
St. Louis, MO 63121
Office address:
Room 312, 3
Publications | People and photos | Projects @ Github | Acknowledgements
Select Publications
- Adhikari, Badri. Thinking Beyond Chatbots’ Threat to Education: Visualizations to Elucidate the Writing or Coding Process. Education Sciences 13(9), 922 (2023).
- Adhikari, Badri. A fully open-source framework for deep learning protein real-valued distances. Nature Scientific Reports 10, 2045–2322 (2020).
- Adhikari, Badri. DEEPCON: protein contact prediction using dilated convolutional neural networks with dropout. Bioinformatics 36, 470–477 (2020).
Select Grants
- 2024, $100,000, CooperVision, “Using Deep Neural Networks to Predict Success in Orthokeratology Lens Fitting,” Role: Co-PI
- 2020, $163,535, National Science Foundation, “CISE CRII: Deep Learning Methods for Protein Inter-residue Distance Prediction”, Role: PI
- 2020, $256,496, National Aeronautics and Space Administration, “STTR Phase1: Autonomous Environmental Monitoring and Management Platform for Remote Habitats”, Role: Co-PI
Select Awards
- 2024, “Outstanding Teaching Award,” Department of Computer Science, University of Missouri-St. Louis.
- 2022, “Outstanding Research Award,” Department of Computer Science, University of Missouri-St. Louis.
Teaching
Many of my lecture recordings are in Youtube.
Courses
- Interpretable Machine Learning
- Deep Learning
- Artificial Intelligence
- Advanced Data Structures and Algorithms
- Principles of Data Visualization