Machine intelligence has recently demonstrated superhuman performance in domains such as autonomous driving, visual object recognition and chess. In this talk, I will highlight some of the major advances in machine learning over the past five years and discuss how the Lee Group is applying Machine Learning to problems in the natural sciences.
The topics covered will include predicting the outcomes of chemical reactions, searching for novel solar energy materials as well as the use of techniques from statistical physics to better understand the learning process in artificial neural networks.