Internship | Federated Learning without Forgetting

About this position

When using federated learning, many organizations collaboratively train a model, without the need to share data, making it a much more secure alternative compared to traditional approaches. This is especially important in document authentication, where data often includes highly confidential information such as passports and breeder documents. However, the field of document authentication faces challenges because the data is gradually evolving. For example, a passport recognition model trained on passports from 20 years ago will behave poorly when used today, because personal documents have seen many updated versions (approximately a new version per country every 5 to 10 years). This change in data leads to two aspects: (1) one document type may have multiple valid versions for the layout, and (2) the model will remember outdated classes learned during the initial training phase. To address these issues, it is desired to control what the model learns and forgets, without affecting knowledge on the other classes. Techniques such as continual learning (also known as lifelong learning or learning without forgetting) could offer a solution. We are especially interested in how these techniques translate to federated learning. Our main question here is: "how can we control what a model, trained in a federated way, learns and forgets, without reducing knowledge on untouched classes?"

What will be your role?

This project is part of ongoing research at TNO, where we have several projects on federated learning and document authentication. First, we expect you to do a literature study on the state-of-the-art of learning without forgetting in federated learning, where you will identify a fitting literature gap. You will define and implement a method to demonstrate your findings, and relate it to the literature. During your internship you will write a thesis to document your research. If applicable and time allows it, a paper publication with your findings may also be possible.

You will perform this assignment within TNO’s Intelligent Imaging department. The Intelligent Imaging department is a passionate, creative, and dedicated team of professionals (60 people) specialized in developing groundbreaking applications in the field of computer vision. Our team members have diverse backgrounds, ranging from the medical field to artificial intelligence. Intelligent Imaging is a young and growing department which has built up a lot of expertise over the past years in AI and deep learning.

What we expect from you

You are in the final stages of your master's degree in artificial intelligence, computer science, physics, mathematics, electrical engineering, or a similar degree. Prior experience with computer vision, image analysis, programming (Python), artificial intelligence/deep learning is appreciated. Additionally, we would like you to come to our office in The Hague (Oude Waalsdorperweg 63) at least 2 days per week, but preferably more often.

Your supervision team will consist of two experienced TNO colleagues who are actively involved in ongoing research projects at TNO. They have experience in state-of-the-art federated learning, computer vision, image analysis, and artificial intelligence research, as well as supervising students in internships and graduate projects.

Please include the following practical information in your cover letter:

• Whether you are looking for an internship or a graduation project.
• The preferred duration of your project (flexible in the range of 6 to 12 months).
• Your desired start date (flexible, but due to the required security screening the earliest possible start date is three months after submitting your application).

What you'll get in return

You want an internship opportunity on the precursor of your career; an internship gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Furthermore, we provide:

• A highly professional, innovative internship environment, within a team of top experts.
• A suitable internship allowance (615 euro for wo-, hbo- and mbo-students, for a full-time internship).
• Possibility of eight hours of free leave per internship month (for a full-time internship).
• A free membership of Jong TNO, where you can meet other TNO professionals and join several activities, such as sports activities, (work-related) courses or the yearly ski-trip.
• Use of a laptop.
• An allowance for travel expenses in case you don’t receive an OV-card.

TNO as an employer

At TNO, we innovate for a healthier, safer and more sustainable life. And for a strong economy. Since 1932, we have been making knowledge and technology available for the common good. We find each other in wonder and ingenuity. We are driven to push boundaries. There is all the space and support for your talent and ambition. You work with people who will challenge you: who inspire you and want to learn from you. Our state-of-the-art facilities are there to realize your vision. What you do at TNO matters: impact makes the difference. Because with every innovation you contribute to tomorrow’s world.

Muriel Spek, van der

• E-mailadres: muriel.vanderspek@tno.nl