Machine Learning & Artificial Intelligence for Chemists

New

Artificial Intelligence (AI) in the context of chemistry has a long history. The first application was in mass spectrometry, but AI is now being applied to a diverse range of problems, including reaction prediction and drug discovery. Machine learning (ML) is an important part of AI, and the aim of this course is to introduce some of the main ML concepts and techniques, and to illustrate their use in contemporary chemical applications. By the end of the course, you should be able to judge which of these ML techniques are appropriate for a given task and evaluate the results.

The lectures will be supplemented with two practical sessions (which require a basic knowledge of R) and two assignments.

Some of the reading material will be taken from parts of the following books: Bishop, C.M., Pattern Recognition and Machine Learning, Springer, 2006. Hastie, T., Tibshirani, R. & Friedman. J., The Elements of Statistical Learning (2nd edn), Springer, 2009. Mohri, M., Rostamizadeh, A. & Talwalkar, A., Foundations of Machine Learning (2nd edn), MIT Press, 2018. Murphy, K.P., Machine Learning: A Probabilistic Approach, MIT Press, 2012. Russell, S.J. & Norvig, P., Artificial Intelligence: A Modern Approach (3rd edn), Pearson, 2010.

Number of sessions: 7

• AI, ML and types of learning
• Examples from chemistry
• Induction, trees and random forests
• Optimising and evaluating ML systems
• Designing an ML project
• Regression and neural networks
• Transduction, support vector machines and kernel methods
• Ensembles, boosting and reinforcement learning