The National Science Agenda has awarded a 5 million euro grant to CORTEX – the Center for Optimal, Real-Time Machine Studies of the Explosive Universe. The CORTEX consortium of 13 partners from academia, industry and society will make self-learning machines faster: to figure out how massive cosmic explosions work, and to innovate systems that benefit our society.

Published by the editorial team, 11 June 2019

Machine learning has rapidly become an integral part of our lives. It is now commonly used for speech recognition and information retrieval. This is also true in science, for detecting patterns in nature and the Universe. But the need is growing rapidly for such machines to respond quickly, for example in self-driving cars and for responsive manufacturing. On a more fundamental level, self-learning machines help us unveil a dynamical Universe we did not know existed until recently. Bright explosions appear all over the radio and gravitational-wave sky. Many citizens and scientists are curious to understand where these come from.

“In CORTEX we aim to solve these open problems by bridging fundamental research to society", says dr. Joeri van Leeuwen (ASTRON), the project lead. “We can only reach these ambitious goals if academic, applied, public and industry partners work together.”

The 5 million euro grant from the Nationale Wetenschapsagenda: Onderzoek op Routes door Consortia (NWA-ORC) program will thus fund research at partners ASTRON, Nikhef, SURF, Netherlands eScience Center, Universiteit van Amsterdam, Radboud Universiteit Nijmegen, Centrum Wiskunde & Informatica, IBM Nederland B.V., BrainCreators B.V., ABN AMRO N.V., NVIDIA, NOVA, and Stichting ILT; in cooperation with Rijksmuseum, Thermo Fisher Scientific, and Leiden University.

“Gravitational waves whipped up by merging black holes and neutron stars peak for less than a few seconds, maybe several times per month”, says dr. Sarah Caudill (Nikhef), “and fast self-learning machines can help us recognise the events as they occur.” Responding quickly to these using radio telescopes can help to better understand how the universe works, dr. Antonia Rowlinson (University of Amsterdam & ASTRON) explains: “Using machine learning, we will pick out their radio afterglow from thousands of sources and, by watching how they change, we can determine the vast energies that must be involved.”

“CORTEX is unique in that we subsequently translate the latest mathematical and computer-science discoveries in faster and better computing for industry and society", says dr. Raymond Oonk from SURF. Maarten Stol from BrainCreators B.V. concurs: “Both for startups and for large companies, machine learning on large data streams is essential. Only in a collaboration such as CORTEX can cutting edge science make its way to innovation in business.”

For video quotes, please visit the CORTEX YouTube channel.

Sources
Related

Latest tweets

Daily image of the week

On June 13-17, the LOFAR Family Meeting took place in Cologne. After two years LOFAR researchers could finally meet in person again. The meeting brings together LOFAR users and researchers to share new scientific results.
https://www.astron.nl/dailyimage/main.php?date=20220621

Our renewed ‘Melkwegpad’ (Milky Way Path) is finished! The new signs have texts in Dutch on the one side and in English on the other side. The signs concerning planets have a small, 3D printed model of that planet in their centre.
https://www.astron.nl/dailyimage/
#Melkwegpad @RTVDrenthe

Daily image of the week

The background drawing shows how the subband correlator calculates the array correlation matrix. In the upper left the 4 UniBoard2s we used. The two ACM plots in the picture show that the phase differences of the visibilities vary from 0 to 360 degrees.

Daily image of the week: Testing with the Dwingeloo Test Station (DTS)
One of the key specifications of LOFAR2.0 is measuring using the low- and the highband antenna at the same time. For this measurement we used 9 lowband antenna and 3 HBA tiles.
https://www.astron.nl/dailyimage/main.php?date=20220607

searchtwitter-squarelinkedin-squarebarsyoutube-playinstagramfacebook-officialcrosschevron-right