Machine Learning (ML) is a branch of artificial intelligence that allows machines to learn without being programmed to do so. Its capability to make accurate predictions based on other samples, which were previously learnt, makes it a very useful tool in many fields of science such as medicine, sports and stock market. However, achieving accurate predictions is a computationally demanding task which needs of high computing power. In this context, high-performance computing (HPC) is a must to carry out ML algorithms in a reasonable time.

SIBILA Server takes advantage of both technologies to provide users with a powerful predictive tool. Several ML models are available and a large set of configuration parameters facilitate the configuration of the tasks. In addition, the server applies the concept of explainable artificial intelligence (XAI) to present the results in a way that users will be able to understand. A collection of interpretability approaches are implemented to identify the most relevant features that were taken into consideration by the model in order to make the prediction.

The server is open to all users. Registration is not necessary, and a detailed report with the prediction results are sent to the user by email. This is the first public domain server for machine learning predictions.

Subscribe to our Newsletter in order to get updates at https://bio-hpc.eu.