Computer Science & AI

Machine Learning

Computers are capable of making incredibly accurate predictions on the basis of machine learning. In other words, these computers can learn without intervention once they have been pre-programmed by humans. At LIACS, we explore and push the borders of what a revolutionary new generation of algorithms can achieve.

Deep Learning

The goal of the LIACS Media Lab (LML) at Leiden University is to conduct state-of-the-art research in the areas of deep learning, artificial intelligence and computer vision. Their research spans the dominant kinds of media information which are images, video, audio and text, or "multimedia". One of the most ubiquitous society problems is how to browse and search the vast mountain of multimedia information from diverse sources such as smartphones, digital libraries, cultural heritage collections and the Internet. Even though acquiring the multimedia information is straightforward, there currently are no effective solutions for finding multimedia information using everyday common queries. The group has an emphasis on using deep learning and computer vision methods to classify images into human-understandable text and involves using the content such as pixels in images and advanced artificial intelligence and deep neural network algorithms to determine who or what is in the image.

Automated Design and Analysis of Algorithms

The Automated Design and Analysis of Algorithms (ADA) research group pursues the development of Artificial Intelligence techniques that complement, rather than replace, human intelligence. In particular, their research is focussed on methods for the automated design and analysis of algorithms for computationally challenging problems, leveraging human creativity, advanced machine learning and optimisation methods, and lots of compute cycles. They work on a broad range of problems, including propositional satisfiability (SAT), AI planning, mixed integer programming (MIP), the travelling salesperson problem (TSP), supervised and semi-supervised machine learning, as well as a range of real-world applications.
More information about ADA

Reinforcement learning

The Reinforcement Learning lab conducts research into Reinforcement Learning and Intelligent Combinatorial Algorithms. The group teaches courses in Reinforcement Learning, Robotics, Deep Learning, Game Design, and Advanced Data Mining. It is an open group, with members from bachelor and master students working on their thesis to faculty members. Their interests range from reinforcement learning, games, multi-objective optimization, neural networks, and robotics.
More information about the Reinforcement Learning lab