News ⎜ Contact Us

Machine learning techniques for science

Machine learning Techniques for science

Science is undergoing a data explosion and the advent of Artificial Intelligence and Machine Learning techniques is revolutionising the way scientists tackle their research. Simulations and observations now generate Petabytes of data and machine learning is providing novel and powerful methods for analysing those experimental datasets and extracting essential science in ways that have not been possible before.

Description

The course provides a practical, and hands-on introduction to the concepts, methods, and toolkits for applying machine learning to fundamental scientific problems. It is held virtually over five consecutive mornings, lectures, including work examples to reinforce the concepts, and hands-on practical sessions are delivered. The practical sessions, where participants have access to dedicated GPU resources, are meant to ensure that participants learn to apply their newly learned skills to practical problems stemming from physics, astronomy, and other domains. The course covers:

      • Conventional machine learning techniques (such as decision trees),

      • Neural and deep neural networks, the cornerstone of modern AI

      • Generative models to enable you to generate synthetic, yet realistic, datasets with labels, and

      • Debugging and RSE aspects of machine learning

    The course is provided by STFC’s Scientific Machine Learning Research Group (SciML) in the Scientific Computing Department.

    Timetable

    day 1: classical machine learning
    09:00 – 09:30
    Introduction to Machine Learning
    09:30 – 10:15
    Lecture – Supervised Learning Techniques
    10:15 – 11:15
    Hands-On Practical
    11:15 – 11:45
    Break
    11:45 – 13:00
    Lecture – Unsupervised Learning Techniques

    Day 2: Neural Networks and Convolutional Neural Networks

    09:00 – 09:45
    Lecture – Neural Networks
    09:45 – 10:45
    Hands-On Practical
    10:45 – 11:15
    Break
    11:15 – 12:00
    Convolutional Neural Networks
    12:00 – 13:00
    Hands-On Practical

    Day 3: Generative Models

    09:00 – 09:30
    Introduction to Generative Models
    09:30 – 10:00
    Autoencoders
    10:00 – 10:30
    Hands-On Practical
    10:30 – 11:15
    Break
    11:15 – 12:15
    Variational Autoencoders & Generative Adversarial Networks
    12:15 – 13:00
    Hands-On Practical

    Day 4: Advanced Topics

    09:00 – 09:30
    Long Short-Term Memory Networks
    09:30 – 10:30
    Hands-On Practical
    10:30 – 10:45
    Transformers & Large Language Models
    10:45 – 11:15
    Break
    11:15 – 11:45
    Lecture – Generative Adversarial Networks (GANs)
    11:45 – 12:00
    Reinforcement Learning
    12:00 – 13:00
    Debugging and Exploring ML Solutions

    Day 5: Using Large-scale Resources

    09:00 – 09:45
    Using Large-Scale Resources & Cloud
    09:45 – 10:30
    Hands-On Practical
    10:30 – 11:00
    Break
    11:00 – 12:00
    Discussions and Closure

    Prerequisites

    Basic programming skills in Python.

    Previous Course Testimonials

    “I found the course to be the ideal mix between theory and practical examples. Very informative on how to use ML for cutting-edge science research questions.”

    “This course was the perfect introduction to machine learning from a scientific perspective; instructors were enthusiastic and very helpful, and the lectures and materials were approachable for someone with no previous experience while remaining detailed enough to be of practical use. I felt I gained a good overview of a range of important techniques and algorithms and will certainly apply the knowledge gained during my chemistry PhD.”