Dr. Muhammad Rashid received his PhD in Computer Science from the University of Turin, Italy, where his research focused on Explainable Artificial Intelligence (XAI) and the interpretation of deep learning models for computer vision. He is currently a Research Fellow and Machine Learning Researcher specializing in explainable AI, visual anomaly detection, trustworthy machine learning, and interpretable computer vision systems.
His research investigates reliable and structure-aware explanation methods, including Shapley-based image feature attribution, improved sampling strategies for local explanations, and explainable anomaly-detection frameworks. He has developed machine-learning solutions for safety-critical industrial and robotic environments, including real-time anomaly detection, visual safety monitoring, and explainable decision-support systems.
His broader research experience spans object detection and recognition, facial recognition, scene understanding, image analysis, and medical imaging applications involving gastrointestinal diseases, skin cancer, brain, lung, eye, and bone analysis. He has also worked on artificial-intelligence applications in agriculture and healthcare.
Dr. Rashid is actively involved in developing reproducible research tools, open-source machine-learning software, and practical AI systems that connect methodological research with real-world deployment. His current interests include explainable and trustworthy AI, visual anomaly detection.
Dr. Muhammad Rashid received his PhD in Computer Science from the University of Turin, Italy, where his research focused on Explainable Artificial Intelligence (XAI) and the interpretation of deep learning models for computer vision. He is currently a Research Fellow and Machine Learning Researcher specializing in explainable AI, visual anomaly detection, trustworthy machine learning, and interpretable computer vision systems.
His research investigates reliable and structure-aware explanation methods, including Shapley-based image feature attribution, improved sampling strategies for local explanations, and explainable anomaly-detection frameworks. He has developed machine-learning solutions for safety-critical industrial and robotic environments, including real-time anomaly detection, visual safety monitoring, and explainable decision-support systems.
His broader research experience spans object detection and recognition, facial recognition, scene understanding, image analysis, and medical imaging applications involving gastrointestinal diseases, skin cancer, brain, lung, eye, and bone analysis. He has also worked on artificial-intelligence applications in agriculture and healthcare.
Dr. Rashid is actively involved in developing reproducible research tools, open-source machine-learning software, and practical AI systems that connect methodological research with real-world deployment. His current interests include explainable and trustworthy AI, visual anomaly detection.