What will you be doing?
Explainable Artificial Intelligence is an emergent research field that copes with the lack of transparency of AI systems, by providing human understandable explanations for the underlying Machine Learning models. Do you want to make AI understandable?
In the context of Artificial Intelligence, Machine Learning (ML) is a rapidly growing field. There has been a surge of high-performance models for classification and prediction. Still, the application of these models in high-risk domains is more stagnant due to lack of transparency and trust: there is a disconnect between the black-box character of these models and the needs of the users. Explainable Artificial Intelligence (XAI) has recently emerged to provide solutions to this issue by attempting to create understandable explanations for the reasoning of a black-box model. TNO is actively researching in the field of XAI.
Last year, to give you some background of our work, we worked on extracting useful explanations for predictions made by black-box ML models. For example, two explanation extraction methods were built: one that provides example-based explanations  and one that provides contrastive explanations . The former entails motivating a decision by providing examples of similar situations. It is widely recognized as an effective way to provide explanations, as it bears a close resemblance to the way humans think. The latter type of explanation aims to answer contrastive questions i.e. why did the ML model predict class A instead of class B (contrast class). Furthermore, these explanation methods were evaluated empirically in their practical usefulness.
This year our XAI project is bigger and has different sub-projects with different focus. One of these sub-projects focuses on providing effective explanations such that users can spot errors in the classification logic, further we aim to enable user correction onto the classification logic. In the literature, enabling user correction is generally done through active and coactive learning in which the user is able to augment the training-set with new labeled instances and correct the prediction made by the ML model, respectively. We aim to go a step further and allow the correction of the logic of the ML model directly.
If you are interested and want to dive into the research world of XAI, this is your chance. Together, we can figure out the specific topic that you will work on. You can do the internship as part of your Master thesis or as a regular internship. The internship duration is typically 6-9 months.
 Adhikari, A., Tax, D. M., Satta, R., & Fath, M. (2018). Example and Feature importance-based Explanations for Black-box Machine Learning Models. arXiv preprint arXiv:1812.09044.
 van der Waa, J., Robeer, M., van Diggelen, J., Brinkhuis, M., & Neerincx, M. (2018). Contrastive Explanations with Local Foil Trees. arXiv preprint arXiv:1806.07470
What do we require of you?
- Background in Computer Science/AI or related fields.
- Experience with Python and ML libraries such as sklearn, pandas, tensorflow…
- Experience with deep learning.
- Good academic skills.
What can you expect of your work situation?
TNO is an independent research organisation whose expertise and research make an important contribution to the competitiveness of companies and organisations, to the economy and to the quality of society as a whole. Innovation with purpose is what TNO stands for. With 3000 people we develop knowledge not for its own sake but for practical application. To create new products that make life more pleasant and valuable and help companies innovate. To find creative answers to the questions posed by society. We work for a variety of customers: governments, the SME sector, large companies, service providers and non-governmental organisations. Working together on new knowledge, better products and clear recommendations for policy and processes. In everything we do, impact is the key. Our product and process innovations and recommendations are only worth something if our customers can use them to boost their competitiveness.
What can TNO offer you?
You want to work on the precursor of your career, an internship provides you with the opportunity to take a good look at your prospective future employer. TNO also 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 internship, and be given the scope for you to exceed yourself and your expectations. We also provide suitable compensation for internships. Click here
to find more info about internships at TNO.
Has this vacancy sparked your interest?
Then please feel free to apply on this vacancy! For further questions don’t hesitate to contact us.
Note that applications via email and third party applications are not taken into consideration.
Contact: Maarten Kruithof
Phone number: +31 (0)88-86 68147