Nettsider med emneord «Unsupervised learning»

The main objective of this work is to improve the utility of new small satellites for Earth Observation (EO), by researching machine learning techniques to obtain improved and useful detection, classification, and identification capabilities from space.

The adaptive immune system records all past and ongoing battles with disease and infection in the form of immune memory, stored in the form of DNA of immune receptors of adaptive immune cells. However, deciphering these signals is a grand challenge of immunology, requiring sophisticated machine learning.

The spatial configuration of continents and its temporal evolution exert a fundamental control on Earth’s evolution. Before 130 Ma, plate motions can only be quantified through the study of paleomagnetism, however, individual paleomagnetic data cannot constrain longitude.

In MASSIVE, the project team aims at improving glacier mapping and surface glacier mass balance estimation techniques with the help of machine learning, especially deep learning. We will develop the methodology for glaciers in Norway, Svalbard, the European Alps and the Himalayas and then expand it to regions with different glacier characteristics.

The aim of this project is to determine the effectiveness of antidepressant treatment in pregnant and postpartum women, as well as the longer-term metabolic safety of these drugs in pregnancy on the offspring.

Colorectal cancer (CRC) symptoms are unspecific – often
emerging when the disease is no longer curable. Screening
reduces CRC mortality, but current screening tests need improvement to be more accurate and less costly and invasive. The overall aim of the CRCbiome study is to discover gut microbiota biomarkers for colorectal cancer screening.

For maritime safety surveillance we develop new approaches
based on the availability of large arrays of sensors, which
monitor condition and performance of vessels, machinery, or
power systems.

AI, statistical models and machine learning methods can often be seen as black boxes to those who construct the model and/or to those who use or are exposed to the methods.

In a wide range of applications, monitoring data streams for faults or changes in behavior (called anomalies) is of great importance.

BigInsight produces innovative solutions for key data-driven challenges facing our consortium of private, public and research partners, by developing original statistical and machine learning methodologies.