Internship | Enabling battle-speed hypothesis assessment

Internship | Enabling battle-speed hypothesis assessment

About this position

In military operations, a superior information position and thorough understanding of the situation enables the commander to make better and timely decisions, that the opponent gains a military advantage. Situational understanding focuses on interpreting the information collected about a situation and discovering the “why” behind it. What does the collected information imply about the operational environment? Can we predict what is happening or what is going to happen? To answer the last question, TNO has developed the Hypothesis Assessment Framework (HAF) model, which is a hypothesis testing method whose computation mechanism is based on the Dempster-Shafer method [1],[2]. A hypothesis can be regarded as a possible explanation, i.e. a possible “why”, of the situation. By collecting information and providing it to the HAF model, an indication of the most likely hypothesis can be obtained. In addition, the HAF model can quantify ignorance and conflicting information. The latter provides insights to the commander on the constantly changing operational environment and highlights when the provided information is not in line with the model. The HAF model is currently implemented in the statistical programming language R and operates effectively, but the computation time significantly increases with increasing amounts of information added to the model architecture. More efficient GPU algorithms for Dempster-Shafer, implemented using Python and CUDA, exist [3]. In this internship, you will investigate how the computational mechanism of the HAF model can be accelerated using the computational advantages of a GPU. References [1].Shafer, G. (1976). A Mathematical Theory of Evidence. Princeton university press. [2].P. Smets and R. Kennes, ‘The transferable belief model,’ Artificial intelligence, vol. 66, no. 2, pp. 191–234,1994. [3].Rico, N., Troiano, L., & Díaz, I. (2024). Efficient GPU-algorithms for the combination of evidence in Dempster–Shafer theory. Future Generation Computer Systems, 154, 465-478.

What will be your role?

The goal of this assignment is to establish the HAF model architecture in Python with CUDA to increase the computational power and efficiency. You will first get acquainted with Dempster-Shafer and its GPU implementation. To enable the implementation, you will investigate how the method in literature can be adjusted so that it matches the computational mechanism of the HAF model. You will then implement the adjusted method in Python and CUDA. The performance of the accelerated model architecture will be tested by means of a use case.

The assignment is part of a multi-disciplinary project and will be performed within TNO’s Intelligent Imaging department, which is part of the Unit Defense, Safety and Security. 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

This assignment combines methods from mathematics (Dempster-Shafer and AI) and computer science (GPU). Do you have experience or want to gain more experience in working with GPU programming, mathematical methods and AI? And do you want to make a positive contribution to decisions taken in military operations? Then this position may be a fit for you!

Requirements:

• You are following a HBO or university education in a relevant field, for example computer science, software engineering, applied mathematics, artificial intelligence etc.
• You have experience in programming in Python and on a GPU.
• You have experience in working with mathematical models and AI.
• You like to collaborate in a multi-disciplinary project in the field of military intelligence.
• The duration of the internship project is 6 months.

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.

At TNO we encourage an inclusive work environment, where you can be yourself. Whatever your story and whatever unique qualities you bring to the table. It is by combining our unique strengths and perspectives that we are able to develop innovations that make a real difference in society.