Nettsider med emneord «Bayesian machine learning»

The objective of StREP is to provide a comprehensive and unified account of the decision to request public votes and the consequences thereof for observed behaviour.

Greenhouse gas seepage into the oceans is a major environmental challenge.

While Machine Learning algorithms have in recent years seen great progress, there are still scenarios in which they fail to be as robust and flexible as animals and humans.

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.

LATICE aims to advance the knowledge base concerning land atmosphere interactions through improved model representation of snow, permafrost, hydrology and large-scale vegetation processes representative of high latitudes, including; 1) New ground observations (gap filling using ML); 2) Land surface model parametrization using data science methods; 3) Seasonal snow cover dynamics using data assimilation and Earth observations (e.g. satellite data, drones).

Exploring the fundamental constituents of the Universe physicists are faced with very serious calculational bottlenecks. To compare new physics models to data we need to perform very computationally expensive calculations in quantum field theory (QFT).

We live in a Universe composed of a large variety of chemical elements. The element distribution we observe, and in particular the diverse abundances of atomic nuclei, tells a fascinating story of nucleosynthesis events that have taken place throughout the 13.7-billion-year-long history starting with the Big Bang.

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.

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.

We develop and apply methods based on machine learning for chemistry and materials science. At the method level, our focus is on data (datasets computed with quantum mechanics methods), representations (graphs based on electronic structure theory), and models (graph neural networks and boosted trees).

Bayesian methods have recently regained a significant amount of attention in the machine community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using Bayesian approach: Parameter and prediction uncertainty become easily available, facilitating rigid statistical analysis. Furthermore, prior knowledge can be incorporated.