Scope Compliance Uncertainty Estimate

1 code implementation • 17 Dec 2023 • Al-Harith Farhad, Ioannis Sorokos, Mohammed Naveed Akram, Koorosh Aslansefat, Daniel Schneider

The zeitgeist of the digital era has been dominated by an expanding integration of Artificial Intelligence~(AI) in a plethora of applications across various domains.

Autonomous Vehicles

Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations

1 code implementation • 13 Nov 2023 • Koorosh Aslansefat, Mojgan Hashemian, Martin Walker, Mohammed Naveed Akram, Ioannis Sorokos, Yiannis Papadopoulos

Machine learning is currently undergoing an explosion in capability, popularity, and sophistication.

Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring

1 code implementation • 11 Jul 2022 • Al-Harith Farhad, Ioannis Sorokos, Andreas Schmidt, Mohammed Naveed Akram, Koorosh Aslansefat, Daniel Schneider

Limitations in setting SafeML up properly include the lack of a systematic approach for determining, for a given application, how many operational samples are needed to yield reliable distance information as well as to determine an appropriate distance threshold.

BIG-bench Machine Learning Traffic Sign Recognition

StaDRe and StaDRo: Reliability and Robustness Estimation of ML-based Forecasting using Statistical Distance Measures

2 code implementations • 17 Jun 2022 • Mohammed Naveed Akram, Akshatha Ambekar, Ioannis Sorokos, Koorosh Aslansefat, Daniel Schneider

This work focuses on the use of SafeML for time series data, and on reliability and robustness estimation of ML-forecasting methods using statistical distance measures.

Time Series Time Series Analysis

Dynamic Risk Assessment for Vehicles of Higher Automation Levels by Deep Learning

no code implementations • 20 Jun 2018 • Patrik Feth, Mohammed Naveed Akram, René Schuster, Oliver Wasenmüller

Vehicles of higher automation levels require the creation of situation awareness.