From A to B via a Synthesis of Rare-Event Sampling and Machine Learning
Explore the intersection of rare-event sampling and machine learning in molecular sciences through this insightful lecture by Mark Tuckerman from New York University. Delve into the applications of machine learning in theoretical and computational molecular sciences, focusing on finding reaction coordinates and generating pathways between basins on high-dimensional free energy surfaces. Review collective-variable based enhanced sampling techniques and compare various machine learning models, including kernel methods, neural networks, decision-tree approaches, and nearest-neighbor schemes. Gain valuable insights through specific examples from materials science and biomolecules, demonstrating the power of synergistic approaches in advancing molecular research.