Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

The Institut Laue-Langevin Part of Project on Autonomous Experiments

  • New algorithm enables more efficient acquisition of high-value datasets

Neutron scientists at the Institut Laue-Langevin (ILL), in collaboration with the CAMERA team at the Lawrence Berkeley National Laboratory (LBNL), have successfully validated an autonomous data acquisition system enabling more efficient, accurate data collection over shorter timescales. The most recent results using the new software have been published in Nature Reviews Physics.

gpCAM has been developed by the CAMERA team and uses a novel, self-learning algorithm based on Gaussian process regression, enabling gpCAM to make autonomous decisions on the best next point to perform measurements and collect data.

Recommended AI News: Impact Celebrates One Year in Germany as It Continues Its Strategic Expansion

According to Martin Boehm, instrument scientist at the Institut Laue-Langevin: “For spectrometry this offers a new way of doing experiments. We saw the instruments evaluate the next optimum points for measurements to take place, which has halved the measuring time in our test runs. And we are just at the beginning of this development.”

Related Posts
1 of 19,876

In contrast to current machine learning or artificial intelligence technologies, where algorithms are trained on very large data sets (‘big data’), gpCAM can be trained and conditioned with a comparatively very small set of data points. The aim is to work with fewer but more informative data points, reducing experiment time and costs, and facilitating data interpretation for the researchers.

Recommended AI News: NTT Research Takes Quantum-Leap Into Next-Gen Neuro-Computing

Scientists working in different scientific fields across the world, using very different scientific instrumentation, increasingly rely on autonomous experiments. This was recently discussed at the international conference on autonomous experiments organised by Marcus Noack, the main developer of gpCAM and leading researcher in autonomous experiments at the Lawrence Berkeley National Laboratory in the USA.

Marcus commented: “It is part of CAMERA’s mission to bring together interdisciplinary co-design teams from around the world to tackle high-impact scientific challenges. ILL has had a significant impact on the success of that mission by lending expertise, time and equipment to push autonomous discovery in neutron scattering to the next level. We hope to continue this work for years to come.”

Recommended AI News: TeamViewer Integrates With Jamf to Remotely Manage Apple Devices

Comments are closed.