Internship | Exploiting attention to streamline the training of deep neural networks applied to radar data

What will be your role? Deep learning techniques usually thrive when large sets of labelled data are available. In the radar domain, labelled data tend to be scarce depending on the application area. By exploiting expert knowledge it may be possible to improve the training process and overall performance when using only small labelled data sets. From experience an expert may know what features are more distinctive or less distinctive given the specified target classes. In addition, the characteristics of the background clutter in different radar measurements may vary. This can affect the training process, which is undesired if the background clutter does not contain information about the target class (as is typically the case). In these cases, an expert might be able to give the neural network a nudge in the right direction. The goal of this assignment is to investigate what type of expert knowledge would be useful to streamline the training process and how this knowledge should be used in that process. For this assignment, visualisation techniques, highlighting the image pixels that are used for classification, can be a supporting tool. Subsequently neural attention can be applied to focus the training process on those image pixels that actually contain relevant information. Radar measurements of different target classes are available for this assignment. You will perform this assignment in the Department of Radar Technology. We are a passionate and creative group of professionals (60 people) dedicated to the specification, development and evaluation of innovative, high-performance MMICs, miniaturised and integrated RF subsystems, antennas and front-ends. The department is at the heart of novel, game-changing radar system and signal processing concepts for the military, space and civil domains. What we expect from you You are in the final stages of your degree in artificial intelligence, computer science, physics, mathematics, electrical engineering or a similar degree and have some track record in the field of signal processing or computer vision. You have experience in programming in Matlab and/or Python, you are pragmatic and focused on making things work. Next to technical expertise we value communication skills and a results-driven attitude. 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.

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.