Thesis Worker 30 hp - Conformal Prediction for Counterfactual Generation

Teknik, data och digitalt · Data, AI och analys · Datavetenskap · Maskininlärning

I korthet

This thesis position focuses on Conformal Prediction for Counterfactual Generation within TRATON's IoT platform, aiming to validate plausible counterfactual explanations for anomaly detection. The role involves implementing anomaly detection and counterfactual methods, developing conformal approaches, and evaluating their robustness and statistical guarantees.

Ansvarsområden

Implement a baseline anomaly detection framework and establish datasets and evaluation procedures.
Implement baseline counterfactual methods and evaluate their ability to produce valid, proximal, and plausible counterfactuals.
Investigate how conformal prediction can be incorporated into counterfactual generation or filtering.
Explore alternative nonconformity measures and strategies for determining whether generated counterfactuals are supported by the observed data distribution.
Systematically evaluate generated counterfactuals in terms of validity, proximity, sparsity, plausibility and conformal coverage/validity.
Study the trade-offs between producing counterfactuals close to the original observation and counterfactuals well supported by representative data.
Evaluate the proposed methods across different anomaly detection models, datasets, and/or data distributions to understand when conformal guarantees and generated explanations remain reliable.

Krav

Masters programmes in Machine Learning, Data Science, Computer Science, Complex Adaptive Systems or similar.
CV, personal letter, and copies of grades.

Önskade kvalifikationer

Conformal Prediction for Counterfactual Generation
Counterfactual explanations
Anomaly detection models
Optimization
Uncertainty quantification

Förmåner

Build relationships for the future.
Many of today's employees began their Scania career with their degree project.
Opportunity to work at the intersection of explainable AI, anomaly detection, optimization and uncertainty quantification.

Färdigheter

Anomaly DetectionMachine LearningData ScienceComputer ScienceConformal PredictionCounterfactual Explanations

#Conformal Prediction#Counterfactual Generation#Anomaly Detection#Machine Learning#Data Science#Computer Science#IoT#Explainable AI#Uncertainty Quantification#Masters Programme

Om Scania Group

Scania is a world-leading provider of transport solutions committed to a better tomorrow. Our purpose is to drive the shift towards a sustainable transport system. In doing so, we are creating a world of mobility that’s better for business, society and our environment. Employing more than 50,000 people in about 100 countries, Scania’s research and development is concentrated in Sweden, while production takes place in Europe and South America.

Se alla lediga jobb hos Scania Group Läs mer om Scania Group Webbplats