We do research on machine learning algorithms, including but not limited to deep neural networks, and their applications in pattern recognition.
Interactive Intelligent Systems
We design, develop and analyze agent technologies that integrate different aspects of intelligence such as reasoning, decision making and learning. Our aim is to support human decision makers in complex and dynamic environments, which also require the design of effective human computer interaction.
We investigate how sensorimotor information is and/or should be processed to generate intelligent behavior on biological and artificial systems from a computational viewpoint with strong emphasis on embodiment, development and learning. Human-robot synergistic adaptation and learning is also studied for synthesizing autonomous and semi autonomous dexterous behaviors on robots.
Natural Language Processing
We study wide range of topics from Natural Language Processing and Information Retrieval. Some current research areas include but not limited to Text Mining, Statistical Machine Translation, Semantic Analysis and Social Media Analysis.
We develop learning algorithms that enable computers to extract knowledge from data and exploit this knowledge to make predictions for future cases. Our aim is to discover new schemes to perform learning in the computer environment that are known to be used by the human brain, such as deep (layered) learning, learning from few samples, and learning from incomplete data.