June 16, 2024 UMD Home FabLab AIMLab
MLMR 2022
7th Annual
Machine Learning for Materials Research Bootcamp
Hybrid, August 8 - 12, 2022



Registration is Open!

MLMR 2022 registration is now open. Click here to register!


Save the date!

MLMR 2022 will be hybrid this year, August 8-12, 2022. If you have any questions, please contact: mlmr@umd.edu.

MRS Endorsed Meeting Logo Past attendees map

Bootcamp (Days 1-4)

Four days of lectures and hands-on exercises covering a range of data analysis topics from introduction to python and data pre-processing to advanced machine learning analysis techniques. Example topics include:

  • Identifying important features in complex/high dimensional data
  • Visualizing high dimensional data to facilitate user analysis.
  • Identifying the 'descriptors' that best predict variance in functional properties.
  • Quantifying similarities between materials using complex/high dimensional data
  • Identifying the most informative experiment to perform next.

Hands-on exercises will include practical use of machine learning tools on real materials experimental data (scalar values, spectra, micrographs, etc.)

Scientists will also demonstrate how they performed recently published research, from loading and preprocessing data to analyzing and visualizing results, all in Jupyter notebooks. Day 4 will include hand-on exercises on how to use the AFLOW database online.

Workshop (Day 5)

Topic: Workshop on Advanced ML Techniques for Materials Discovery

Bootcamp Schedule

The bootcamp will run daily from 9:00am - 5:00pm (EDT). It will be live on zoom, and recorded sessions will be made available to participants afterwards.

Day 1:
  • Welcome and High-level intro to Machine Learning
  • Introduction to Python
  • Data Preprocessing
    • Filtering / Noise Smoothing
    • Normalization / Standardization
    • Background Subtraction
    • Feature Extraction: e.g. Cross-correction, wavelets, edges, boundaries, shapes
Day 2: Unsupervised Learning
  • Review of Linear Algebra and Notations
  • Dissimilarity Measures
  • Latent Variable Analysis
  • Spectral Unmixing / Matrix Factorization under constraints
  • Clustering
Day 3: Supervised Learning
  • Data Handling
  • Algorithms:
    • Regularized Linear Regression
    • The Kernel Trick
    • Gaussian Processes
    • Neutral Networks
    • Decision Trees & Ensemble Learning
    • Symbolic Regression
Day 4: Active Learning, DFT, and Natural Language Processing
  • Introduction to DFT and Tutorial on AFLOW
  • Machine Learning for DFT-based Data
  • Natural Language Processing
  • Active Learning, Bayesian Optimization, and Gaussian Processes

Thursday evening bootcamp dinner and poster session (Kim Engineering Building Rotunda). This year, we will resume the poster session: “Machine Learn This.” Please bring a poster (optional) and let us know the title of your poster.

Day 5: Workshop on Advanced ML Techniques for Materials Discovery


If you are a student (graduate, undergraduate, or high school), write to us first at mlmr@umd.edu, so we can send you a student discount code BEFORE you register. Write to us also for an academic discount code if you work at an academic institution (university, etc.) BEFORE you register.

If you are planning to attend via Zoom online, there is a discount for this also. Please write to ask for this code BEFORE you register.

Fee: $230 - read above for discount options

Register Here


This year's event will be hybrid with in-person meetings taking place at the Edward St. John Learning and Teaching Center (room 2204) at the University of Maryland, College Park campus, while simultaneously meeting via Zoom (daily from 9am - 4:30pm).



A. Gilad Kusne A. Gilad Kusne National Institute of Standards & Technology Materials Measurement Science Division
Alexei Belianinov Alexei Belianinov Sandia National Laboratories Ion Beam Laboratory
Daniel Samarov Daniel Samarov National Institute of Standards and Technology Information Technology Laboratory
Ichiro Takeuchi Ichiro Takeuchi University of Maryland, College Park Department of Materials Science & Engineering

Colleges A. James Clark School of Engineering
The College of Computer, Mathematical, and Natural Sciences

Communicate Contact Us
Contact the Webmaster
Follow us on TwitterTwitter logo

Links Privacy Policy

Copyright The University of Maryland University of Maryland