Ericsson

Join our Team

About this opportunity:

Modern machine learning models (e.g., deep neural networks, ensembles) often operate as black boxes, achieving high accuracy but offering no insight into their reasoning. This lack of transparency limits trust, accountability, and regulatory compliance. Explainable AI (XAI) addresses these challenges by seeking interpretable alternatives. Rule-based explanations are particularly promising, as they can be easily understood, validated, and aligned with human or domain knowledge. The key problem is how to systematically transform a black-box model into a rule-based white-box representation without losing predictive fidelity.

In this thesis work, the task is to develop and evaluate an approach that takes a black-box model as input and produces a set of interpretable rules that approximate it. The approach will allow:

− Measurement of fidelity and coverage compared to the original model.

− Optional integration of background knowledge in rule generation.

− User control over complexity (e.g., limiting the maximum number of rules).

What you will do:

• Perform a literature survey to gain familiarity with and review existing XAI and rule-extraction methods.
• Design and implement a prototype algorithm that generates rules from black-box predictions.
• Develop a configurable framework for black-to-white box transformation by integrating user constraints and background knowledge into rule search.
• Evaluate the approach on benchmark datasets using fidelity, coverage, accuracy, and interpretability metrics.
• Analyse relevant trade-offs between fidelity, coverage, accuracy, and rule set cardinality, as well as complexity.
• Documentation of the work.
• The thesis will be concluded with a result presentation for the Ericsson team.

The skills you bring:

• Currently pursuing a master’s degree in an AI/ML-related data science program, or in a related field such as computer engineering, electrical engineering, physics engineering, or similar.
• Basic proficiency in computer science and in programming with Python.
• Good knowledge of machine learning, probability theory, and statistics.

Why join Ericsson?

At Ericsson, you´ll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what´s possible. To build solutions never seen before to some of the world’s toughest problems. You´ll be challenged, but you won’t be alone. You´ll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.

What happens once you apply?

Click Here to find all you need to know about what our typical hiring process looks like.

Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.

Primary country and city: Sweden (SE) || Stockholm

Req ID: 774148