Prof. Kulik will describe their efforts to accelerate the discovery of novel transition metal containing materials using machine learning. She will discuss how they have leveraged experimental data sets through both text mining and semantic embedding to uncover relationships between structure and function in molecular catalysts and metal-organic frameworks. Then she will describe how they have leveraged large datasets of synthesized materials to uncover those with novel function in polymer networks. She will describe how they demonstrate the success of their design strategy through macroscopically visible changes in network scale properties.