Home
Center for Data Science
CEDAS research

Research in Data Science

CEDAS data science research
Data Science is a multi-disciplinary field that capitalizes on theories, methods, techniques, and algorithms from information technology (ICT), including visualization and machine learning. Data Science builds upon a foundation of theories from computer science, mathematics (in particular statistics), and social sciences, etc., to enable a large variety of applications, including predictive analytics and business intelligence, data-driven sciences (big data science), and artificial intelligence.
Photo:
CEDAS, UiB

Data Science is a multi-disciplinary field that capitalizes on theories, methods, techniques, and algorithms from information technology (ICT), including visualization and machine learning. Data Science builds upon a foundation of theories from computer science, mathematics (in particular statistics), and social sciences, etc., to enable a large variety of applications, including predictive analytics and business intelligence, data-driven sciences (big data science), and artificial intelligence.

Data Science and Artificial Intelligence
are two tightly related fields, sharing major research challenges and resulting technologies, with machine learning as a notably prominent example. Teaching computers human-like, intelligent behavior is increasingly often achieved by letting AI systems learn from large and rich data, critically depending on know-how and skills from data science.

About CEDAS and Data Science:
In order to coordinate, strengthen, and prioritize local research efforts in data science, we are operating and extending a new research center for data science, CEDAS, together with a growing number of partners. While CEDAS first and foremost focuses on the urgently needed principal research in data science, it also embraces research-based higher education in data science (BSc., MSc., and PhD) as well as applications of data science, including data-driven science such as bioinformatics as well as applications in businesses and the society.  Furthermore, CEDAS is also addressing important questions related to software and hardware infrastructure, needed to facilitate successful data science. Orthogonally to CEDAS’ technical and mathematical research directions, humanitarian and societal questions (ethics, RRI, etc.) also are an important part of the CEDAS research focus.

Mission and Vision of CEDAS:
UiB’s Center for Data Science, CEDAS, provides, advances, and integrates key competences on algorithms, artificial intelligence, machine learning, semantic and social information technologies, statistics, and visualization, doing excellent basic and applied research in data science, solving urgent data science challenges, and educating data scientists for academia and business. Within the mid-2020s, CEDAS has become the leading Scandinavian research center on data science and enjoys an excellent reputation on an international level due to its research and education.

CEDAS research directions

We have identified five research directions in data science, which CEDAS will pursue with particular emphasis:

Foundations of Machine Learning
we aim at a rigorous theoretical understanding of machine learning solutions and their behavior, as well as at design of new algorithms based on this understanding.

Visual Data Science
by integrating interactive visual data exploration, statistical manifold learning, and topological data analysis, we aim at enabling the user to access critical structures in rich data through interactive visualization.
 
Connected Data Science
we aim at understanding and predicting the outcome and behavior of complex systems from data on their components and their interactions at multiple levels of detail with a particular focus on applications in biomedicine.

Behavioral Data Science
on the basis of implicit and explicit data traces, left behind by users, we aim at understanding user and group behavioral patterns for simulation and prediction.
   
Statistical Foundations
we aim at understanding statistical properties of data science and machine learning with a particular focus on uncertainty and its relation to modeling and prediction.