Main navigation
- Programs
- Subjects
- Universities
- Destinations
- Advice
Global research into developing intelligent machines is progressing at a remarkable pace. Our contributions focus on merging breakthroughs in deep learning, symbolic reasoning, computer vision, natural language processing, and robotics. This involves developing systems that synthesize diverse data types such as video, text, images, audio, and satellite data. We also investigate minimally supervised learning methods that extract meaning from raw data, like interpreting words and text by analyzing video descriptions.
Supporting this comprehensive approach, we conduct foundational theoretical research in qualitative spatial reasoning, expanding our groundbreaking work on the Region Connection Calculus (RCC). Additional areas include developing algorithms for human pose detection, automated text alignment and segmentation, user modeling and customization, language analysis using text corpora, and robotics applications, with special emphasis on manipulation and path planning.