Item 1 van 1

Seminar series in Numerical Analysis

Our seminar series is starting again, this year we're back on campus!

The Numerical Analysis seminars are a series of lectures to showcase and foster state-of-the-art research in the fields of computational sciences and engineering, mathematical modelling, and applied mathematics. These lunch lectures take place on a monthly basis, the dates are announced below. If you want to sign up for the monthly invitation, please sign up for our newsletter.

Sign up to our newsletter

Gebruik de volgende webcal om de feed toe te voegen aan de kalender of kopieer de link om handmatig te abonneren.

webcal://www.tudelft.nl/ewi/over-de-faculteit/afdelingen/applied-mathematics/numerical-analysis/events/seminars-in-numerical-analysis?tx_lookupfeed_feed%5Baction%5D=ical&tx_lookupfeed_feed%5Bcontroller%5D=Feed&tx_lookupfeed_feed%5Blimit%5D=15&tx_lookupfeed_feed%5BlookupUid%5D=729698&type=1657271091&cHash=c783c790e2c6b23bc03edb821e9c4b05

Meer info over webcal.

13 december 2024 12:30 t/m 13:15

[NA] Andrea Brugnoli: TBA

TBA

17 januari 2025 12:30 t/m 13:15

[NA] Richard Löscher: TBA

TBA

14 februari 2025 12:30 t/m 13:15

[NA] Amanda Howard: Multifidelity, domain decomposition, and stacking for improving training for physics-informed networks

Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can be difficult or impossible to train accurately for some systems of equations. One way to improve training is through the use of a small amount of data, however, such data is expensive to produce. We will introduce our novel multifidelity framework for stacking physics-informed neural networks and operator networks that facilitates training by progressively reducing the errors in our predictions for when no data is available. In stacking networks, we successively build a chain of networks, where the output at one step can act as a low-fidelity input for training the next step, gradually increasing the expressivity of the learned model. We will finally discuss the extension to domain decomposition using the finite basis method, including applications to newly-developed Kolmogorov-Arnold Networks.

16 mei 2025 12:30 t/m 13:15

[NA] Martin Campos-Pinto: TBA

TBA

Organizers

D. (Deepesh) Toshniwal

A. (Alexander) Heinlein

In Conversation With

The accompanying interview series of the Numerical Analysis seminars.

Seminar Archives
Photo by Alexander Popov on Unsplash