BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning What Matters: Patterns\, Predictions\, and Actions for Ma
 terials - Dr Kevin Maik Jablonka\, Friedrich Schiller University Jena (Ger
 many)
DTSTART:20260223T143000Z
DTEND:20260223T150000Z
UID:TALK243298@talks.cam.ac.uk
CONTACT:Dr Fabian Berger
DESCRIPTION:Materials discovery faces a fundamental challenge: small\, but
  systematic effects shape material performance\, yet these patterns are to
 o complex to encode explicitly in traditional approaches. Machine learning
  offers a path forward by learning to capture the tacit and fuzzy dimensio
 ns of materials behavior that guide expert intuition.\n\nIn this talk\, I'
 ll present a framework for translating patterns into predictions\, and pre
 dictions into actionable design decisions. I'll show how we can mine diver
 se materials data to construct robust training sets\, develop models\, and
 —critically—evaluate whether these models actually work for real-world
  tasks. Through applied examples\, I'll discuss how rigorous evaluation re
 veals when models capture meaningful patterns versus when they just develo
 p fuzzy heuristics via pattern matching.\n\nThe goal isn't just better pre
 dictions\, but reliable tools that help us design materials that work in p
 ractice\, not just on paper.\n
LOCATION:https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHptUXlRSkppQT0
 9
END:VEVENT
END:VCALENDAR