This research group is a highly skilled and dynamic team of experts in the fields of deep learning, machine learning, computer vision, and social robotics. Their research focuses on developing innovative and cutting-edge technologies that can transform industries and change the way people live and work.
At the heart of the group’s work is deep learning, which involves building advanced neural networks that can learn from vast amounts of data and make intelligent decisions. The team is constantly pushing the boundaries of deep learning, exploring new architectures, algorithms, and techniques to improve accuracy, efficiency, and scalability.
Machine learning is another core area of research for the group, which involves developing algorithms that can learn from data and make predictions or decisions. Their work in machine learning is highly interdisciplinary, combining ideas from computer science, statistics, and optimization to solve complex problems in areas such as natural language processing, speech recognition, and recommendation systems.
Computer vision is also a key area of focus for the research group, as they strive to develop intelligent systems that can interpret and understand visual data. This includes developing algorithms for object detection, image classification, and facial recognition, as well as more advanced tasks such as scene understanding and video analysis.
Finally, the group’s work in social robotics involves developing robots that can interact with humans in social settings, such as homes, schools, and hospitals. This involves a range of technical challenges, including developing natural language processing algorithms, designing human-like gestures and facial expressions, and building intuitive interfaces for human-robot interaction.
Reciently, the group has been working on Large Language Models (LLMs), using them to solve several engineering tasks
Overall, the research group is a highly motivated and collaborative team of experts who are passionate about pushing the boundaries of AI and robotics. Their work has the potential to transform industries, improve people’s lives, and revolutionize the way we interact with technology.
- Deep learning
- Large Language models (LLMs)
- Object recognition
- Assistive technologies
- Social robotics
- Efficient methods for three dimensional data
- Visual, topological and metric localization and mapping
- Medical imaging managing and processing
- Traditional computer vision methods