MetaSimulation of NonEquilibrium Processes
Recent developments in Machine Learning (ML) and Artificial Intelligence (AI) have revolutionized how we approach science and engineering. For instance, ML and AI have considerably accelerated the discovery of new materials for catalysis and applications in solar or nuclear energy. ML and AI have enabled the high-throughput screening of nanoporous materials for sustainable energy solutions, as energy carriers through hydrogen storage, or for carbon capture and sequestration. This course will provide a practical introduction to the machine learning concepts, methods, and tools to STEM students. The course will cover the fundamentals of supervised, unsupervised, and semi-supervised methods, including regression models, neural networks, modern deep learning, ensemble models, and reinforcement learning. Examples will be drawn from the entire spectrum of energy applications to illustrate the applications of ML approaches. The hands-on use of Python notebooks will be a key aspect of the course
Semester Taught: Fall 2022 & 2023
In this course, we focus on how AI and ML approaches shed light on the biochemical mechanisms underlying cellular processes. The course starts with an introduction to the basics of widely used ML methods, with practical examples of how ML models can be set up using Python notebooks. We then explore how ML and AI can further our understanding of cellular biochemistry, help elucidate multicellular processes, and guide the design of artificial biomimetic systems. Students will work on a semester-long project and gain first-hand experience in building a ML model on the topic
Semester Taught: Spring 2023 & Spring 2024