The Department of Chemical and Biomolecular Engineering welcomes Dr. Nick Sahinidis, John e. Swearingen Professor from Carnegie Mellon University, as a part of the ChBE Spring Seminar series. His seminar, titled “ALAMO: Machine Learning from Data and First Principles,” will take place on Thursday, April 19th 2018 from 2:00-3:00pm in Earle 100.
We have developed the ALAMO methodology with the aim of producing a tool capable ofusing data to learn algebraic models that are accurate and as simple as possible. ALAMO relies on (a) integer nonlinear optimization to build low-complexity models from input-output data, (b) derivative-free optimization to collect additional data points that can be used to improve tentative models, and (c) global optimization to enforce physical constraints on the mathematical structure of the model. We present computational results and comparisons between ALAMO and a variety of learning techniques, including Latin hypercube sampling, simple least-squares regression, and the lasso. We also describe results from applications in CO 2 capture that motivated the development of ALAMO.