licentiate

My licentiate thesis, Machine Learning for Predictive Modeling and Abstraction in Industrial-Scale Systems, is published as number 384 in the Mälardalen University Press Licentiate Theses series (ISBN 978-91-7485-758-0) and is openly available in DiVA. The licentiate seminar was held on 15 June 2026 at Mälardalen University in Västerås, with Professor José Javier Berrocal Olmeda as opponent.

The thesis is a compilation of four papers, all listed on the publications page: neural network input abstraction (AISoLA 2023), conformal CPU load forecasting (COMPSAC 2025), machine-learning-based cache miss prediction (STTT 2025), and HASCO (AEiC 2026).

The licentiate proposal was approved by Professor Mobyen Uddin Ahmed at Mälardalen University on 2 October 2025.

Machine Learning for Predictive Modeling and Abstraction in Industrial-Scale Systems

Machine learning is increasingly called upon to guide decisions in critical industrial applications. Its predictive power promises efficiency and adaptability, yet its black-box nature and lack of guarantees pose risks in contexts where behavior must remain analyzable and safe.

This thesis addresses how machine learning can be strengthened to become not only powerful, but also accountable, explainable, and usable by engineers in practice. Key contributions include:

  • Neural Network Abstraction: Formally identifying and removing inputs with little effect on outcomes, producing simpler, bounded, analyzable models.
  • Conformal Prediction with Shapley Values: Providing coverage guarantees and tracing load contributions back to individual tasks for safety-relevant insight.
  • Data-Driven Cache Simulator: Reproducing hardware behavior at a fraction of the computational cost.
  • HASCO (Hybrid AI Simulation Compiler): An end-to-end pipeline combining all principles, compiling natural-language accident reports into executable simulation scenarios.

These contributions establish a path toward machine learning that becomes a transparent partner in the industrial workflow, rather than remaining an opaque black box.