Noor khan completed Machine Learning for Automotive Safety

Built a complete perception-validation dossier for a synthetic Aurora-7 detector: defined detection by IoU ≥ 0.5, scored aggregate and VRU-specific precision/recall, exposed a sharp recall collapse in night and occluded slices, and translated the top misses into ISO 21448 SOTIF chains with concrete mitigations. Finished with an evidence-based GO-WITH-CONDITIONS verdict and a grounded comparison to the Uber ATG Tempe crash.

• Leakage-Free Detection Definition
• Honest Safety Metric Evaluation
• Per-Condition Failure Triage
• ISO 21448 SOTIF Reasoning