Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Machine Learning for Materials (Lecture 1)

Aron Walsh
July 15, 2023

Machine Learning for Materials (Lecture 1)

Aron Walsh

July 15, 2023
Tweet

More Decks by Aron Walsh

Other Decks in Science

Transcript

  1. Aron Walsh
    Department of Materials
    Centre for Processable Electronics
    Machine Learning
    for Materials

    View Slide

  2. New Era of Materials Research
    Agrawal and Choudhary, APL Materials 4, 053208 (2016)
    The research toolkit for materials science
    and engineering is expanding

    View Slide

  3. Computer Revolution
    Chris Hendon
    (now: University of Oregon)
    Keith Butler
    (now: STFC/SciML)
    Analytical Engine
    Automated calculations
    Charles Babbage (1837)
    “The science of operations has its
    own truth and value”
    Ada Lovelace (1840)

    View Slide

  4. Computer Revolution
    Chris Hendon
    (now: University of Oregon)
    Keith Butler
    (now: STFC/SciML)
    https://www.apple.com

    View Slide

  5. Computer Revolution
    Chris Hendon
    (now: University of Oregon)
    Keith Butler
    (now: STFC/SciML)
    https://www.apple.com

    View Slide

  6. Exascale Supercomputing
    Chris Hendon
    (now: University of Oregon)
    Keith Butler
    (now: STFC/SciML)
    https://top500.org
    Exascale computing refers to 1018 floating point operations per second; https://top500.org

    View Slide

  7. Powerful Statistical Techniques
    Chris Hendon
    (now: University of Oregon)
    Keith Butler
    (now: STFC/SciML)
    Using GPT-3 via https://github.com/hwchase17/langchain

    View Slide

  8. Efficient Research Workflows
    Correa-Baena et al., Joule 2, 1410 (2018)
    The integration of computational techniques can
    accelerate materials discovery & development cycles

    View Slide

  9. Course Contents
    1. Course Introduction
    2. Materials Modelling
    3. Machine Learning Basics
    4. Materials Data and Representations
    5. Classical Learning
    6. Artificial Neural Networks
    7. Building a Model
    8. Recent Advances in AI
    9. and 10. Research Challenge

    View Slide

  10. What is Machine Learning (ML)?
    Statistical algorithms that learn from training data
    and build a model to make predictions
    Data types
    Materials features can be binary (e.g. stability),
    categorical (e.g. symmetry), integer (e.g.
    stoichiometry), continuous (e.g. rate)
    Learning types
    Unsupervised (identify patterns), supervised (use
    patterns), reinforcement (maximise reward)

    View Slide

  11. What is Machine Learning (ML)?
    Statistical algorithms that identify and
    use patterns in multi-dimensional datasets
    Image from “How Machines Learn” by Helen Edwards

    View Slide

  12. What is Machine Learning (ML)?
    Statistical algorithms that operate on
    multi-dimensional arrays of numerical data
    Image from http://karlstratos.com; note the true definitions are more nuanced
    7 8 3
    1
    7 2 3
    4 8 6
    7 8 9
    [1 7] ⋯ [6 4]
    ⋮ ⋱ ⋮
    [5 6] ⋯ [2 8]
    𝑥 𝒙𝒊
    𝒙𝒊𝒋
    𝒙𝒊𝒋𝒌

    View Slide

  13. What is Machine Learning (ML)?
    Statistical algorithms that operate on
    multi-dimensional arrays of numerical data
    Image from “How Machines Learn” by Helen Edwards
    𝑦1
    𝑦2
    𝑦3
    𝑥11
    𝑥12
    𝑥13
    𝑥14
    𝑥15
    𝑥21
    𝑥22
    𝑥23
    𝑥24
    𝑥25
    𝑥31
    𝑥32
    𝑥33
    𝑥34
    𝑥35
    𝑔1
    𝑔2
    𝑔3
    𝑔4
    𝑔5
    =
    3✖1
    matrix
    3✖5
    matrix
    5✖1
    matrix

    View Slide

  14. Why Machine Learning (ML)?
    Many problems are difficult to solve using standard
    techniques, e.g. combinational expansions
    Non-deterministic polynomial hard (NP-hard)
    Challenging class of computational problems, where finding
    an efficient solution remains an open and difficult task
    Fast Marching Method: J. Andrews and J. A. Sethian, PNAS 104, 1118 (2007)
    Travelling salesman: find the shortest route that visits each city once and returns home

    View Slide

  15. Why Machine Learning (ML)?
    Many problems are difficult to solve using standard
    techniques, e.g. combinational expansions
    Some relevant challenges in materials science:
    Reaction engineering
    Navigate configurational space of reactants & products
    Crystal structure prediction
    Find the optimal 3D structure(s) for a given composition
    Materials design
    Achieve target functionality within chemical constraints

    View Slide

  16. Why Machine Learning (ML)?
    Solid-solutions are used to control structure and
    properties, e.g. (1-x)ZnO + (x)ZnS à ZnO1-x
    Sx
    ML techniques can be used to sample this massive configurational space
    Mixed sites in the supercell
    N = 16: 12,870
    N = 32: 6×108
    N = 64: 1.8×1018
    !
    ! !
    2 2
    N
    N N
    æ öæ ö
    ç ÷ç ÷
    è øè ø
    Number of
    configurations
    for ZnO0.5
    S0.5
    A wurtzite crystal with a
    partially occupied anion site

    View Slide

  17. Image from https://vas3k.com/blog/machine_learning
    ML Model Map

    View Slide

  18. Special thanks to Anthony Onwuli, Zhenzhu Li, and Calysta Tesiman for assistance
    Source Material for Course
    ML content available from many sources, including
    blogs, research papers, repositories, and textbooks
    The slides are a skeleton, fleshed out with lectures, activities, and reading
    General Specialist

    View Slide

  19. A. L. Samuel, IBM Journal, 211 (1959)
    Brief History of Machine Learning
    The term was coined by Arthur Samuel in 1959
    “It is now possible to devise learning schemes which will
    greatly outperform an average person and that such learning
    schemes may eventually be economically feasible”

    View Slide

  20. W. S. McCulloch and W. Pitts, Bull. Math. Biophys. 5, 115 (1943)
    Brief History of Machine Learning
    An artificial neuron had been proposed in 1943
    “Every net, if furnished with a tape, scanners connected
    to afferents to perform the necessary motor-operations,
    can compute only such numbers as can a Turing machine”

    View Slide

  21. A. M. Turing, Mind 236, 433 (1950)
    Brief History of Machine Learning
    In 1950, Alan Turing proposed a
    “Learning Machine” that could become intelligent
    “I PROPOSE to consider the question, Can machines think?”

    View Slide

  22. ML in Materials R&D
    Growing field combining traditional industry,
    large technology companies, and start-ups

    View Slide

  23. Course Assistants
    Dr Zhenzhu Li
    Schmidt AI in Science Fellow
    (Co-instructor)
    Irea
    Mosquera-Lois
    Xia
    Liang
    Anthony
    Onwuli
    Yifan
    Wu

    View Slide

  24. Course Assessment
    Aim for working knowledge of ML with
    weekly practical sessions and coursework
    Electronic notebooks
    Submitted as a pdf on Blackboard
    (deadline of 5pm Monday after each class)
    Research challenge
    Mini project to complete
    (details in Lecture 9)

    View Slide