Prof. Anima Anandkumar

Hi. How flexible/sensitive is this framework to the changes in geometries and meshes? For example, say I want to add/remove a feature, like a hole or a fillet, or place an obstacle to divert the flow or change the mesh resolution adaptively in an unsteady simulation.

This learns the operator of PDE. So it doesn't rely on mesh and is not resolution dependent. We see high fidelity super resolution capability in our method.

Will you have a video taped seminar of this. I tried reading the paper and lets just say I’m more of a visual learner?

This is actually pretty amazing! Are there any particularly interesting applications you envision for this method?

There are so many interesting ones, so many that I can't count ;) Basically, solutions to problems that require mappings from function spaces (or generally infinite-d spaces) may benefit from this.