You have data and a model, and you want the two to match. What do you do? This has many names - solving inverse problems, parameter estimation, design optimization, model calibration, etc. This is what the JuliaSim Model Optimizer achieves - finding the parameters which cause models to be sufficiently good fits to data. Learn how to define and scale your complex inverse problems through automated model calibration and parameter estimation.
In this webinar, you will learn:
-
How to set up a modeling problem
-
How to create the inverse problem for parameter estimation
-
How to generate and visualize the optimized parameters
Model autocomplete is a feature unique to JuliaSim using the universal differential equation symbolic model recovery mechanism to predict the best model extensions given the associated data. This allows for accelerating the modeler by helping perform the model construction, giving possible next steps in the difficult scientific process.
