ESPCI web site
Soft Matter meets Machine Learning : Using New Machine Learning Algorithms to Unravel Structural and Dynamical Features in Glassy Fluids
Developments in machine learning have opened the door to fully new methods for studying phase transitions due to their ability to extremely efficiently identify complex patterns in systems of many particles. Applications of machine learning techniques vary from the use of developing new ML-based order parameters for complex crystal structures, to locating phase transitions, to speeding up simulations. The rapid emergence of multiple applications of machine learning to statistical mechanics and materials science demonstrates that these techniques are destined to become an important tool for soft matterphysics. In this talk, I will briefly present an overview of the work my group is doing on using ML to study soft matter systems, with a focus on two new applications in the field of glassy materials. Specifically, I will show how a new unsupervised algorithm can find structural variations in glassy materials that turn out to correlate strongly with local dynamics. Secondly, I will present a new strategy to fit the dynamics in glassy systems using a supervised machine learning algorithm.