Jaarprogramma 2017-2018 | Vorige lezing | Volgende lezing | Home
Dinsdag 3 april 2018
Dr. L.C. Filion (Soft Condensed Matter, UU)
Machine Learning in Soft Matter
Machine learning is the art of training a computer program to distinguish patterns in large data sets. Within the physics community, these computer science developments have opened the door to novel methods for studying phase transitions due to their ability to efficiently identify patterns in many-body systems. Highlights include developing order parameters to identify complex crystal structures, locating phase transitions in spin systems, and pinpointing weak spots in colloidal glasses.
In this talk I will introduce the basics of machine learning, explaining the basics of both “supervised” and “unsupervised” algorithms. I will then discuss some applications of these algorithms to soft matter systems. I will finish my talk describing some of the work we are currently doing in Utrecht, where we use both supervised and unsupervised machine learning to help us identify local crystalline order in colloidal systems.
Links:
Jaarprogramma 2017-2018 | Vorige lezing | Volgende lezing | Home