April 2022 Machine Learning for Science Training Course Session Recordings

Dates: 4th April to 8th April 2022

The following links are only available to the attendees of the April 2022 training course. For details of upcoming courses, please follow the DiRAC twitter page.

Please follow the links below to view the recordings of the course lectures.

Classical Machine Learning

Introduction to Machine Learning

Supervised Learning Tequniques

Unsupervised Learning Techniques

Deep Neural Networks

Deep Neural Networks

Convolutional Neural Networks & Pretrained Models

Image Processing

Long Short-Term Memory (LSTM) Networks

Back Propagation and Gradient Descent

Debugging and Exploring ML Solutions

Generative Models

Generative Models Introduction

Generative Models Autoencoders

Generative Models VAEs

Generative Models GANs

Helping you prepare for the future


Dates: 4th April to 8th April 2022, Every Day 09.00 – 13.00

Day 1: Classical Machine Learning

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

Day 2: Deep Neural Networks

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

Day 3: Image Processing

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

Day 4: Generative Models

09:00 – 09:45 Introduction to Generative Models & VAE
09:45 – 10:30 Hands-On Practical
10:30 – 11:00Break
11:00 – 11:45 Lecture – Generative Adversarial Networks (GANs)
11:45 – 12:30Hands-On Practical
12:30 – 13:00 Lecture – Debugging/ Exploring

Helping you prepare for the future

Machine Learning Techniques for Science

4th April 2022 to 8th April 2022

Course: Machine Learning Techniques for Science

Science is undergoing a data explosion and the advent of Artificial Intelligence and Machine Learning techniques is revolutionizing 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.


The course provided a practical, and hands-on introduction to the concepts, methods, and toolkits for applying machine learning to fundamental scientific problems. Held virtually over five consecutive mornings, lectures, including worked examples to reinforce the concepts, and hands-on practical sessions were delivered. The practical sessions, where participants had access to dedicated GPU resources, were meant to ensure that participants learned to apply their newly learned skills on practical problems stemming from physics, astronomy and other domains. The course covered.

  • 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 the machine learning

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

An Outline Timetable can be found here


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.”


Places on the Machine Learning Techniques for Science course are allocated giving priority to individuals who are part of a DiRAC project. If you would like find out how to become a DiRAC user, please see our latest call for proposals.

Registration is now closed.

Follow us on Twitter @DiRAC_HPC for future ML course announcements.

Helping you prepare for the future

Training Overview

At DiRAC, we believe one of our most important responsibilities to our user-base is to offer comprehensive training. The better trained our researcher cohort, the more efficiently we can use our HPC systems, thereby increasing our scientific productivity and generating more research from our existing systems. In addition we can deploy more bleeding-edge and innovative HPC technology in our services, increasing our capability and energy efficiency, and enabling calculations which would otherwise not be feasible.

On this page you can find information on the DiRAC Essentials Level Training and other External Opportunities that will be useful to our users and community.

Essentials Level Training

The DiRAC Essentials Level Training (formerly the DiRAC Driving Licence), is a basic introduction to the principles of HPC and the tools needed to work on an HPC system. The course consists of seven modules covering everything from the Unix Environment to Good Network Practices and is presented as a series of links to external sources that we have selected for you. After working through the modules you will know the Essentials of how to work with, and get the best out of, DiRAC’s HPC systems.

The training is mandatory for those studying for advanced degrees, such as M.Sc. and Ph.D., and those employed as Post-Doctoral Research Assistants/Associates who have less than two years HPC experience. The Essentials Level culminates in a basic on-line test and the training material covers all aspects of HPC competency that are included.

Information on accessing the training and registering for a training account can be found here.

External Opportunties

There are currently no External Opportunities.

Essentials Overview

At DiRAC, we believe one of our most important responsibilities is to offer our community comprehensive training. We have a responsibility to make sure that our HPC resources are used as efficiently as possible and we have an even greater duty of care to make sure you are well trained in advanced IT techniques and are confident in using them.

Essentials Level Training Overview

The DiRAC Essentials Level Training (formerly the Driving Licence), is a basic introduction to the principles of HPC and the tools needed to work on an HPC system. Once you have completed the course you will be able to do more science of higher impact (and we hope you will have more fun as well!). And if we have a well-trained cohort we can invest in much more powerful equipment that is much closer to the bleeding edge and so allow you to generate the new high impact results that will let you and your group to be seen as leaders in your field.

It will also make you much more employable. Real programming and IT skills are making a big comeback both in Academia and Industry. We need to equip you with these skills to improve your career progression. In short, we are trying to create a virtuous circle that will benefit both you, your science and your group’s scientific reputation.

Essentials Level Content

The Essentials Training assumes a familiarity with desktop computers, but no programming, Linux or HPC experience is required. For our users who have a small amount of existing knowledge from undergraduate experience the material is intended to refresh prior knowledge and in some cases, fill in any gaps.  We have seven generic modules and a final module 8 which covers efficiently compiling and running a job on each of our four DiRAC Resources.

The training material for all our modules is presented as a list of links to external sources. There is a vast amount of training material available on the internet, some of which is useful, some of which not so much (!) so we’ve gathered together in one place the links we think will be most helpful to you as you start to use HPC. We have tried to cover the material in both text and video format so there is some overlap, but after working through the modules you will know the Essentials of how to work with, and get the best out of, our HPC systems.

Accessing the Training

We ask all our users to register for an account to get access to our training portfolio. You will also have the option during registration to sign up for direct email alerts for appropriate courses and other training opportunities.

Before you sign up for a Training Account, please take a look at our Data Privacy Policy.

To sign-up for a Training Account, Register Here. If you are a DiRAC User with a SAFE account, we encourage you to use the same username when you register for your Training account.

Once you have registered you can Access the Training Course Content here or through the link in the drop-down ‘Essentials Training’ Menu at the top of the page. 

Essentials Level Test Round: 2021/22

The 2021/22 test round opened on the 17th November 2021 and closed on the 28th February.

The Essentials Level training culminates in a short on-line test – the training material provided covers all aspects of HPC competency that are included in the test.

The Essentials Level Test is mandatory for those who are studying for advanced degrees, such as M.Sc. and Ph.D., and those employed as Post-Doctoral Research Assistants/Associates who have less than two years HPC experience.

The test is graded as follows: 

  • Pass: 70% – the examinee completed the exam successfully
  • Conditional pass: 60-69% – the examinee did not complete the entire exam successfully, but it is believed they are capable of doing so.  They will have three months to re-take the exam and pass.
  • No pass: 59% and below – the examinee was clearly unable to complete the exam on their own. They will be offered additional help by the Director.

Once you have registered you can Access the Test here or from the link in the drop-down ‘Essentials Training’ Menu at the top of the page. 

If you have not taken/passed the test by the deadline we will contact you and your supervisor to discuss your case.  At this point, we will be able to arrange further assistance for you so you can pass the test and continue to use DiRAC resources in your research. Failure to take this test may result in you account on all DiRAC facilities being suspended.


Following the test we will ask you to complete a small number of multiple-choice questions designed to assess how useful you found the training and offer you the option to give us feedback and suggestions. If you took the training we encourage you to take the survey so we can improve the content for future generations.  The survey only takes a couple of minutes to complete.

Data Privacy

We use the information from the survey to help us better understand the needs of our user community and to identify areas where we can improve and more closely target our training offering to those needs. Our aim is to continually develop and innovate DiRAC’s training offering as those needs evolve.

The information you give will not be shared with anyone outside our small training team and we will never share your personal contact information with any external organisation. Your responses to the  survey are fully anonymised before any analysis is undertaken.

Before you apply for a Training Account or take the Essentials Level Test, please take a look at our full Data Privacy Policy.

DiRAC Training All Levels

The DiRAC Training Program
At DiRAC, we believe one of the facility’s most important responsibilities is to offer its user-base comprehensive training.  A well-trained user-base increases the volume and complexity of research that can be carried out and means we can use systems that are closer to the edge of technology, which in turn means that more and better research can be carried out.  

The DiRAC training program has been designed to guide users along a path from very little knowledge to a really good understanding of HPC code development. We recognise that our users predominantly fall into two categories: those who run existing codes, and those that develop and enhance codes, so we have broken up the training into 5 levels of increasingly advanced content.

We do not expect all users to complete the whole program but we do require all new users with less than 2 year’s experience to complete Level 1: Essentials, and the accompanying on-line test by the end of their first year. The program as a whole has been designed so that all new users of HPC systems would benefit from the first three levels, with researchers involved in code development progressing beyond Level 3 as an when the content becomes useful to their Research.

Each level has a corresponding body of material associated with it and currently these resources are sourced from academic institutions and the general IT community. We are still in the process of populating Levels 2 – 5 but we expect these to come on-line as the year progresses

  1. DiRAC – Essentials: An introduction to the key skills needed when using the UK National DiRAC HPC Service and a building block for the further levels.

  2. DiRAC – Researcher: This level will give users the skills to run codes on any DiRAC system.

  3. DiRAC – Advanced Researcher: This level tackles the challenges of replicating another code or advancing your own.

  4. DiRAC – HPC Developer: This level provides the skills needed to start creating robust, well structured and efficient code.

  5. DiRAC – Expert Practitioner: This will enable users to use these codes as efficiently as possible.