Abu Dhabi Machine Learning Season 5 Episode 3
20.03.2025 - Abu Dhabi Machine Learning - ~3 Minutes
When?
- Thursday, March 20, 2025 from 5:00 PM to 8:00 PM (Abu Dhabi Time)
Where?
- ADGM Academy, 20F, Al Maqam Tower, Al Maryah Island, Abu Dhabi
The Meetup page of the event:
Abu Dhabi Machine Learning Meetup Season 5 Episode 3
Another great event with the organisation support of ADIA Lab and ADGM Academy.
Programme:
Talk 1: Advancing AI for Computational Precision Medicine
Abstract: How AI models and frameworks can improve patient outcomes and reduce healthcare costs by integrating multimodal data such as electronic health records and medical imaging.
Speaker: Dr. Farah Shamout is an Assistant Professor of Computer Engineering at NYU Abu Dhabi, leading the Clinical Artificial Intelligence Lab. She is also an Associated Faculty at NYU Tandon School of Engineering and an Affiliated Faculty at NYU Langone Health (Radiology). She completed her PhD at the University of Oxford as a Rhodes Scholar and her BSc in Computer Engineering at NYU Abu Dhabi. Her research focuses on developing machine learning methods for computational precision health, using electronic health records and medical imaging for diagnostics, prognostics, and risk prediction modeling. She specializes in multimodal learning, foundation models, and AI trustworthiness for clinical applications.
Talk 2: Interpreting Foundation Models for Medical Image Analysis
Abstract: A look at the transformative role of foundation models in medical image computing, their challenges, and innovative approaches to interpretability and active learning.
Speaker: Dr. Dwarikanath Mahapatra is a Principal AI/ML Engineer at LocAI with expertise in computer vision and AI for healthcare, particularly medical image analysis and decision support systems. He holds a Ph.D. from the National University of Singapore, and has worked at ETH Zurich, IBM Research Australia, and Inception AI, Abu Dhabi. He has 130+ published papers, 15 patents, and has been recognized in the top 2% of scientists globally. He has won multiple best paper awards and has been acknowledged among the top 30 computer science scientists in the UAE. His research focuses on interpreting foundation models in medical imaging and improving generalization for diverse medical applications.
Talk 3: Large Vision-Language Models (VLMs) revolutionizing the analysis of Earth observation data
Abstract: Introduction of GeoChat, a conversational AI model designed for remote sensing tasks. GeoChat integrates visual and textual information, enabling users to interpret geospatial imagery through scene classification, image captioning, visual question answering, and multi-turn dialogues.
Speaker: Muhammad Sohail Danish is a PhD candidate in Computer Vision at the Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) in Abu Dhabi. His research focuses on Large Vision-Language Models and their applications in Earth Observation. He has contributed to GeoChat, the first grounded large vision-language model for remote sensing, and GeoBench-VLMs, a benchmark for evaluating vision-language models in geospatial tasks. He previously received his MS in Data Science from the Information Technology University (ITU) in Lahore, where he worked on AI for medical imaging and domain generalization.