BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Build the future: Design concrete with machine learning - Bogdan Z
 viazhynski\, TCM Group\, Cavendish Laboratory
DTSTART:20231116T150000Z
DTEND:20231116T160000Z
UID:TALK206485@talks.cam.ac.uk
CONTACT:Stephen Walley
DESCRIPTION:Noise is usually the enemy of machine learning as uncertainty 
 in training data leads to inaccurate predictions.  However\, we develop an
 d validate a machine learning architecture that extracts crucial informati
 on out of the noise itself to improve the predictions. We apply the formal
 ism to specify a concrete mix that has low environmental impact\, and anot
 her concrete mix that has high resistance to carbonation\, and both mixes 
 also fulfil targets on the strength\, density\, and cost. The proposed con
 cretes were then mixed\, set\, and the predicted properties experimentally
  verified. Our generic formalism enables the exploitation of uncertainty i
 n machine learning\, which has a broad range of applications in the physic
 al sciences and beyond.
LOCATION:Mott Seminar Room
END:VEVENT
END:VCALENDAR