Lab Home | Phone | Search
Center for Nonlinear Studies  Center for Nonlinear Studies
 Home 
 People 
 CNLS Staff Members 
 Executive Committee 
 Postdocs 
 Visitors 
 Students 
 Research 
 Publications 
 Conferences 
 Workshops 
 Sponsorship 
 Talks 
 Seminars 
 Postdoc Seminars Archive 
 Quantum Lunch 
 Quantum Lunch Archive 
 P/T Colloquia 
 Archive 
 Ulam Scholar 
 Anastasio Fellow 
 
 Student Requests      
 Student Program 
 Visitor Requests 
 Description 
 Past Visitors 
 Services 
 General 
 
 History of CNLS 
 
 Maps, Directions 
 T-Division 
 LANL 
 
Selma Peterson

CNLS Postdoctoral Research Associate
XCP-AI4ND

AI/ML

Office: TA-3, Bldg 1690, Room 138
Mail Stop: B258
Email: slwanna@lanl.gov

Research highlight

    After years of working as a roboticist deploying off-the-shelf AI and machine learning tools to address DOE mission challenges, I’ve developed a strong desire to build the theoretical foundation necessary to better understand, interpret, and improve these models—particularly their failure modes and reliability guarantees. My goal is to pursue and integrate the mathematical tools that enable such understanding, including probabilistic frameworks, formal verification methods, vector spaces, functional analysis, and related areas at the intersection of probability and geometry, such as differential geometry. I aim to deepen my expertise in these domains, and produce tangible outcomes: user-friendly, open-source tools that help others apply machine learning and AI with greater confidence and transparency.

 Educational Background/Employment:
  • B.S. in Electrical Engineering (BSEE), University of Texas at Austin
  • M.S. in Mechanical Engineering (MSME), University of Texas at Austin
  • Ph.D. in Mechanical Engineering (PhD ME), University of Texas at Austin
  • Employment:
    • 2017 - 2025: Graduate Research Assistant (GRA) – Nuclear and Applied Robotics Group
    • 2017 - 2025: Graduate Research Assistant (GRA) – Los Alamos National Laboratory (LANL)

Research Interests:

  • Machine Learning / Artificial Intelligence
  • Uncertainty Quantification
  • Functional Analysis
  • Inversion
Google Scholar

Selected Recent Publications:

  1. Selma Wanna; Agnes Luhtaru; Ryan Barron; Jonathan Salfity; Juston Moore; Cynthia Matuszek; Mitch Pryor . Let’s Talk About Language! Investigating Linguistic Diversity in Embodied AI Datasets (2025)
  2. Kilian Zepf; Selma Wanna; Marco Miani; Juston Moore; Jes Frellsen; Soren Hauberg; Frederik Warburg; Aasa Feragen . Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification (2024) 10.48550/arXiv.2303.13123
  3. Selma Wanna; Shivansh Sharma; Christina Petlowany; Juston Moore; Mitch Pryor . An Overview of the Hand and Glove Segmentation Dataset (2025)
LANL Operated by the Triad National Security, LLC for the National Nuclear Security Administration of the US Department of Energy.
Copyright © 2003 LANS, LLC | Disclaimer/Privacy