Los Alamos National Laboratory

Los Alamos National Laboratory

Delivering science and technology to protect our nation and promote world stability
Find Expertise logo

Profile Pages

View homepages for scientists and researchers. Explore potential collaborations and project opportunities. Search the extensive range of capabilities by keyword to quickly find who and what you are looking for.

Elisabeth Ann Baseman

Lissa Baseman

Email
Phone (505) 412-4195

Capabilities

  • Biosciences
  • Neural computation
  • Computational Physics and Applied Mathematics
  • Statistics
  • Computer and Computational Sciences
  • High performance computing
  • Exascale
  • Accelerated architecture
  • Machine learning,
  • Data mining
  • High performance computing
  • Information Science and Technology
  • Machine Learning
  • Real and artificial neural systems
  • Classical and quantum communication systems
  • Social networks
  • Network inference
  • Quantum cryptography
  • Quantum Information
  • Quantum key distribution
  • Quantum communication theory
  • Quantum algorithms
  • Nuclear and Particle Physics, Astrophysics, and Cosmology
  • Real-time knowledge extraction
  • Machine learning
  • Science of Signatures - Remote and Standoff Sensing
  • Real-time knowledge extraction
  • Machine learning,
  • High performance computing
  • Real-time knowledge extraction
  • Computer and Computational Sciences
  • Human factors
  • Information Science and Technology
  • Social data analysis
  • Social behavioral analysis
  • Human computation
  • Social and collaborative computing
  • Social media
  • Writing & Editing
  • Teaching (grammar, clear writing, proposals, etc.)

Expertise

 

Machine Learning:

  • Statistical Relational Learning
  • Graphical Models
  • Graph Analysis
  • Interpretable Machine Learning
  • Social Network Analysis

Education

M.S. in Computer Science, University of Massachusetts Amherst

B.A. Summa Cum Laude with Distinction in Computer Science, Amherst College

 

LANL Positions

Lissa Baseman is a machine learning researcher and data scientist at Los Alamos National Laboratory in the High Performance Computing Design group and the Ultrascale Systems Research Center.   She leads efforts in machine learning for high performance computing problems, including memory fault characterization, environmental sensor monitoring, and anomaly detection across the data center.  Lissa’s work prior to joining the HPC Design group at LANL included time at MIT Lincoln Laboratory doing relational learning and social network analysis in the Human Language Technology group, as well as time at LANL’s Center for Nonlinear Studies investigating quantum computing algorithms for machine learning.  Her work in graduate school focused on statistical relational learning for computational social science.  Lissa holds an M.S. in computer science from the University of Massachusetts Amherst and a B.A. in computer science from Amherst College.

 

Professional Societies

Chair, Machine Learning for Computing Systems Workshop.

Advisory Board, Southern Data Science Conference.

Workshop Committee, Supercomputing.

Program Committee, Computational Social Science Society of the Americas,.

 

Publications

Papers

Haque, Abida, Alexandra DeLucia, and Elisabeth Baseman. Markov Chain Modeling for Anomaly Detection in High Performance Computing System Logs. Supercomputing: HPC User Support Tools Workshop, 2017.

Siddiqua, Taniya, Vilas Sridharan, Steven Raasch, Nathan DeBardeleben, Kurt Ferreira, Scott Levy, Elisabeth Baseman, and Qiang Guan. Lifetime Memory Reliability Data from the Field. Defect and Fault Tolerance, 2017. (Best Paper Nominee).

Baseman, Elisabeth, Nathan DeBardeleben, Kurt Ferreira, Vilas Sridharan, Taniya Siddiqua, and Olena Tkachenko. Automating DRAM Fault Mitigation by Learning from Experience. Dependable Systems and Networks, 2017. (Industry Track).

Morrow, Adam, Elisabeth Baseman, and Sean Blanchard. Ranking Anomalous High Performance Computing Sensor Data Using Unsupevised Clustering. CSCI: Symposium on Parallel and Distributed Computing and Computational Science, 2016.

Baseman, Elisabeth, Sean Blanchard, Zonge Li, and Song Fu. Relational Synthesis of Text and Numeric Data for Anomaly Detection on Computing System Logs. International Conference on Machine Learning and Applications, 2016.

Baseman, Elisabeth, Sean Blanchard, Nathan DeBardeleben, Amanda Bonnie, and Adam Morrow. Interpretable Anomaly Detection for Monitoring of High Performance Computing Systems. Knowledge Discovery and Data Mining: Outlier Definition, Detection, and Description on Demand Workshop, 2016.

Guan, Qiang, Nathan DeBardeleben, Panruo Wu, Stephan Eidenbenz, Sean Blanchard, Laura Monroe, Elisabeth Baseman, and Li Tan. Design, Use, and Evaluation of P-FSEFI: A Parallel Soft Error Fault Injection Framework for Emulating Soft Errors in Parallel Applications. Simulation Tools and Techniques, 2016.

Baseman, Elisabeth, Nathan DeBardeleben, Kurt Ferreira, Scott Levy, Steven Raasch, Vilas Sridharan, Taniya Siddiqua, and Qiang Guan. Improving DRAM Fault Mode Characterizaton Through Machine Learning. Dependable Systems and Networks, 2016. (Industrial Track).

Baseman, Elisabeth, and David Jensen. Collaborative Behavior in Social Networks: A Relational Statistical Approach. Neural Information Processing Systems: Networks in the Social and Information Sciences Workshop, 2015.

Baseman, Elisabeth and David Jensen. Exploring Collective Behvior in Social Computation Through Relational Statistical Models. Computational Social Science Society of the Americas, 2016.

Baseman, Elisabeth. Exploring Collective Behavior in Social Computation Through Relational Statistical Models. Masters Thesis, University of Massachusetts Amherst, 2015.

Campbell, William, Elisabeth Baseman, and Kara Greenfield. Content + Context = Classification: Examining the Roles of Social Interactions and Linguist Content in Twitter User Classification. Computational Linguistics: Natural Language Processing for Social Media Workshop, 2014.

Baseman, Elisabeth. Computing with Quantum Physics. Honors Thesis, Amherst College, 2011.

Presentations/Talks

Baseman, Elisabeth. Interpretable Anomaly Detection for High Performance Computing Centers: Monitoring System Logs. Chesapeake Large-Scale Analytics Conference, 2017. (Invited Talk).

Baseman, Elisabeth. Machine Learning for High Performance Computing: Modernizing Monitoring. New Mexico State University, 2017. (Invited Talk).

Baseman, Elisabeth. Interpretable, Context-Aware, Anomaly Detection for High Performance Computing Systems: Monitoring Syslog. Carnegie Mellon University, 2017. (Invited Talk).

Baseman, Elisabeth. Machine Learning for High Performance Computing. Southern Data Science Conference, 2017. (Invited Talk).

Baseman, Elisabeth. Don't be Pipelined. HPC Pipeline Workshop: Diversifying the HPC Workforce, 2017. (Invited Talk).

Baseman, Elisabeth. Machine Learning for Detection and Diagnosis: From Computational Social Science to High Performance Computing. United States Department of Defense, 2016. (Invited Talk).

Baseman, Elisabeth. Little Machines Helping Big Machines: Data Science for High Performance Computing. Los Alamos National Laboratory Ultrascale Systems Research Center Annual Symposium, 2016. (Invited Keynote Talk).

Baseman, Elisabeth. Machine Learning for Automatic Memory Fault Mode Characterization. Silicon Errors in Logic: System Effects, 2016. (Short Talk).

Baseman, Elisabeth. Applications of Relational Learning. MIT Lincoln Laboratory, 2014. (Invited Talk)

Posters

Baseman, Elisabeth. Helping Exascale Computers Help Us: Machine Learning for High Performance Computing.  Neural Information Processing Systems: Women in Machine Learning Workshop, 2017.

Baseman, Elisabeth, Nathan DeBardeleben, Kurt Ferriera, Scott Levy, Steven Raasch, Vilas Sridharan, Taniya Siddiqua, and Qiang Guan. A Machine Learning Approach for Automatic Characterization of Memory Faults. Conference on Data Analysis, 2016.

Baseman, Elisabeth, and David Jensen. Exploring Collective Behavior in Social Computation Through Relational Statistical Models. Neural Information Processing Systems: Women in Machine Learning Workshop, 2016.

Baseman, Elisabeth, Michael Kearns, Stephen Judd, and David Jensen. Dynamic Statistical Models of Collective Social Network Behavior. New England Machine Learning Day, 2014.

Baseman, Elisabeth, Michael Kearns, Stephen Judd, and David Jensen. Statistical Models of Collective Social Network Behavior. Neural Information Processing Systems: Women in Machine Learning Workshop, 2013.

 

Full papers and slides from most talks are available on my personal, non-LANL website.