Adaptive Learning for Machine Learning in Chemistry
This project is part of a multidisciplinary project between chemistry, computer science and psychology, funded by the National Science Foundation. It designed to help people learn about data chemistry by applying machine learning techniques such as Graph Neural Networks and Large Language Models. We focus on important chemistry problems like Molecular Property Prediction, Reaction Prediction, Molecular Property Optimization, Retrosynthesis, and Reaction Optimization.
So far, we have collected a wide range of learning materials, including videos, articles, and academic papers, and written detailed tutorials to guide students in understanding these complex topics. These resources will help researchers in chemistry to develop practical skills and apply machine learning to solve real-world chemical problems.
As an undergraduate involved in this project, your role will be to learn key machine learning techniques and how they apply to solving chemical problems. You will also contribute by improving the clarity and accessibility of our tutorials, ensuring they are understandable for individuals with a chemistry background. Your insights as a learner in chemistry will help bridge the gap between complex technical concepts and practical applications in chemistry, making it easier for others to follow and apply these techniques.
You will work with graduate students in chemistry and computer science to generate training material for machine learning methods and evaluate its suitability for chemists. Preferrable, you should have taken completed the organic chemistry I & II sequence. It is expected that you spend ~5 hours/week per credit you register for on the project, but this does not have to be as a single block of time