machine learning
techniques for science

machine learning techniques for science training

Delivered in collaboration with STFC’s Scientific Machine Learning Group (SCiML), this exciting course provides a practical, hands-on introduction to the concepts, methods, and toolkits available for applying machine learning techniques to fundamental scientific problems. Held virtually over five consecutive half-days, the format consists of short lectures giving worked examples to reinforce principles coupled to hands-on practical sessions applying what has been learnt, mentored by SCiML and DiRAC experts.

TOPICS COVERED

Conventional machine learning techniques (eg. decision trees)
Neural and deep neural networks, the cornerstone of modern AI
Generative models to enable generation of synthetic, yet realistic, datasets with labels.
Variational Autoencoders & Generative Adversarial Networks

The course is provided by DiRAC in collaboration with STFC’s Scientific Machine Learning Research Group (SciML) and is run in an instructor-led format once per annum. However, we are often able to get seats for DiRAC Users on this course when it is run by SCiML for other facilities and these opportunities are advertised by email to all DiRAC users and on our social media channels.

“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 PhD.”

Participant, AI/ML Course 2019