(150b) Alamo

The ALAMO software has been developed in order to infer algebraic models from data obtained from simulations or experiments. ALAMO uses a small number of data points in order to learn models that are as accurate and as simple as possible. The approach relies on optimization techniques in order to: (1) build low-complexity models of systems from input/output data, (2) adaptively sample new simulation or experimental points, and (3) enforce physical constraints on the response function. This tutorial will illustrate ALAMO and its application in several domains.