Inverse materials design can be viewed as a reverse engineering process of material constituents from a user given set of targets characterizing material properties. Machine learning techniques could be used to map a feature space x of material properties to a contextual latent space z over an object space O, and then reconstruct a distinct object space O’ over the latent space z to maximize the context c. In this talk, we introduce a new machine learning tool, called MatFlow, for inverse material design using machine learning. In MatFlow, we first learn the latent space z characterizing a context feature set c. MatFlow then helps identify novel materials O’ over the latent space z with a potential to exceed the contextual threshold theta without destabilizing the latent space. We explain MatFlow features and its capabilities using an application in quantum dye material discovery. The focus of this talk is to introduce a computational strategy to identify z in the context of c and inform the characteristics of z space values of O’ most likely to meet the contextual threshold theta.
Bio: Hasan Jamil is an Associate Professor of Computer Science at the University of Idaho. He has been in the faculty of Wayne State University, Mississippi State University and Macquarie University (Australia) in the past. He obtained the PhD degree in Computer Science from the Concordia University in Montreal, Canada. His research interest is in autonomous systems design using AI and Knowledge Representation technologies. Some of his recent research is in Bioinformatics, Data Integration, Machine Learning, Graph Data Management and Language Design. Most recently, he is also focusing on Large Language Models, Learning Technologies, and Computational Law. He is a member of the IEEE CS, ACM SIGMOD and ALP.