Machine Intelligence

Research in the area of Machine Intelligence aims at developing and studying computational and mathematical models, algorithms, theories, and paradigms for analyzing, understanding, and modeling data, or more generally, reasoning about them. Key methodologies span across different interdisciplinary fields, such as artificial intelligence, symbolic computation, machine learning, signal and image processing, computer vision, and computer graphics. In more detail, in artificial intelligence topics of interest include knowledge representation and reasoning, intelligent agents and multi-agent systems, theorem proving and model building, as well as search methodologies, with emphasis on discrete space search. In machine learning main methods and approaches relate to graphical models, statistical learning and kernel theories, and multiclassifier methods for classification and clustering. In multi-dimensional signal processing the studied techniques regard advanced filtering, feature extraction and segmentation methods, multiresolution and sparse signal representations, time(space)/scale methods, including wavelets, compressive sensing, large scale image characterization and retrieval tools, related to both optical and multimodal images. Computer vision mainly exploits geometric and probabilistic approaches for 3D reconstruction, object recognition, dynamic scene analysis and understanding. Computer graphics relates geometric/physically-based theories for object modeling, shape analysis and visualization.