John W. Sheppard, PhD, FIEEE

Contact Information

Dr. John W. Sheppard
Norm Asbjornson College of Engineering Distinguished Professor
Director, Numerical Intelligent Systems Laboratory
Gianforte School of Computing
365 Barnard Hall
Montana State University
Bozeman, MT 59717
V: +1 406 994 4835
E: john dot sheppard at montana dot edu

A Note to Prospective Graduate Students

Please be advised that my lab is currently at capacity. I am not accepting new graduate students at this time.

Biographical Sketch

Dr. John Sheppard is a Norm Asbjornson College of Engineering Distinguished Professor of Computer Science at Montana State University and previously was the RightNow Technologies Distinguished Professor in Computer Science at MSU. Recently, he was named Interim Director of MSU's Center for Science, Technology, Etchics, and Society (C-STES). He holds a BS in computer science from Southern Methodist University and an MS and PhD in computer science from Johns Hopkins University. In 2007, he was elected as an IEEE Fellow "for contributions to system-level diagnosis and prognosis." Prior to entering academia, he was a Fellow at ARINC Incorporated, a defense aerospace company in Annapolis, MD where he worked for almost 20 years. Dr. Sheppard performs research in probabilistic graphical models, deep learning, evolutionary and swarm-based algorithms, distributed optimization, and applications to system-level test, diagnosis, and predictive health. Recently, his research has expanded into the areas of prostate cancer diagnosis, precision agriculture, and wildfire management. He has published over 200 papers in peer-reviewed conference proceedings and journals as well as two books on the subject of system-level diagnosis. In addition, Dr. Sheppard is active in IEEE Standards activities where, currently, he serves as the chair of the IEEE P2848 Prognostics and Health Management for Automatic Test Systems standards development working group under SCC20. He is also a member of the IEEE P2976 eXplainable AI standards working group.


  • BS, Computer Science (magna cum laude), Southern Methodist University, 1983
  • MS, Computer Science, The Johns Hopkins University, 1990
  • PhD, Computer Science, The Johns Hopkins University, 1997


  • Norm Asbjornson College of Engineering Distinguished Professor in Computer Science, Montana State University
  • Interim Director, Center for Science, Technology, Ethics, and Society (C-STES), Montana State University
  • Lecturer, Computer Science Program, Engineering and Applied Science Programs for Professionals, The Johns Hopkins University

Professional Activities

  • IEEE Fellow
    • IEEE Computer Society
    • IEEE Computational Intelligence Society
    • IEEE Instrumentation and Measurement Society
    • IEEE Standards Association
  • ACM Special Interest Group on Evolutionary Computation (SIGEVO)
  • IEEE Computer Society Liaison to SCC20
  • Member-At-Large, IEEE Computer Society Standards Activities Board
  • Co-Chair, IEEE SCC20, Diagnostic and Maintenance Control Subcommittee
  • Tutorials Chair, IEEE AUTOTESTCON 2017ff
  • Technical Program Chair, IEEE AUTOTESTCON 2001, 2007, and 2011
  • Technical Program Chair, IEEE International Workshop on System Test and Diagnosis, 1998-2000
  • Associate Editor, IEEE Transactions on Instrumentation and Measurement

Research Interests

  • Machine Learning
  • Data Mining
  • Data Science
  • Probabilistic Graphical Models
  • Neural Networks
  • Deep Learning and Deep Feature Extraction
  • Population-based Metaheuristic Search
  • Factored and Distributed Optimization
  • System-Level Fault Diagnosis and Prognosis

Courses Taught

  • Montana State University
    • CSCI 246: Discrete Structures
    • CSCI 440: Database Systems
    • CSCI 446: Artificial Intelligence
    • CSCI 447: Machine Learning: Soft Computing
    • CSCI 500: Seminar in Machine Learning
    • CSCI 546: Advanced Artificial Intelligence
    • CSCI 547: Machine Learning
    • CSCI 548: Reasoning Under Uncertainty
    • CSCI 550: Data Mining
  • Johns Hopkins University
    • 600.335/435: Artificial Intelligence (Homewood)
    • 600.475: Machine Learning (Homewood)
    • 600.735: Seminar in Machine Learning (Homewood)
    • 605.445: Artificial Intelligence (EP)
    • 605.621: Foundations of Algorithms (EP)
    • 605.649: Introduction to Machine Learning (EP)
    • 605.746: Advanced Machine Learning (EP)
    • 605.747: Evolutionary Computation (EP)

Current Graduate Students

  1. Muhammad Arju (PhD Advisee)
  2. Will Jardee (PhD Advisee)
  3. Seyedmojtaba Mohasel (PhD Committee)
  4. Georgio Morales (PhD Advisee)
  5. Nishu Nath (PhD Advisee)
  6. Asad Noor (PhD Advisee)
  7. Gideon Popoola (MS Advisee)
  8. Jordan Schupbach, ABD (PhD Advisee, with Dr. John Borkowski)
  9. Nathan Woods (PhD Committee)

Prior PhD Students

  1. Dr. Stephyn Butcher (2018), Information Sharing and Conflict Resolution in Particle Swarm Optimization Variants, now at GLG.
  2. Dr. Patrick Donnelly (2015), Learning Spectral Filters for Single- and Multi-Label Classification of Musical Instruments, now at Oregon State University, Bend.
  3. Dr. Nathan Fortier (2015), Inference and Learning in Bayesian Networks Using Overlapping Swarm Intelligence, now at Golden Helix.
  4. Dr. Richard McAllister (2020), Extracting Abstract Spatio-Temporal Features of Weather Phenomena for Autoencoder Transfer Learning, now at Weather Stream.
  5. Dr. Benjamin Mitchell (2017), The Spatial Inductive Bias of Deep Learning, now at Swarthmore College.
  6. Dr. Amy Peerlinck (2023), Multi- and Many-Objective Factored Evolutionary Algorithms, now at Western Colorado University.
  7. Dr. Logan Perreault (2017), Improved Scalability and Expressiveness for Continuous Time Bayesian Networks now at Cruise Automation.
  8. Dr. Shane Strasser (2017), Factored Evolutionary Algorithms: Cooperative Coevolutionary Optimization with Overlap, now at Globality, Inc..
  9. Dr. Liessman Sturlaugson (2014), Extensions to Modeling and Inference in Continuous Time Bayesian Networks, now at Boeing Research & Technology.
  10. Dr. Hasari Tosun (2016), Efficient Machine Learning Using Partitioned Restricted Boltzmann Machines, now at Turnitin.
  11. Dr. Scott Wahl (2021), Hierarchical Fuzzy Spectral Clustering in Campaign Finance Social Networks, now a contractor for the University of Illinois.