1 code implementation • 21 Mar 2024 • Janek Gröhl, Kylie Yeung, Kevin Gu, Thomas R. Else, Monika Golinska, Ellie V. Bunce, Lina Hacker, Sarah E. Bohndiek
We used a long short-term memory network to implement a wavelength-flexible network architecture and proposed the Jensen-Shannon divergence to predict the most suitable training dataset.
1 code implementation • 11 Jun 2023 • Janek Gröhl, Thomas R. Else, Lina Hacker, Ellie V. Bunce, Paul W. Sweeney, Sarah E. Bohndiek
We show that training on simulated data results in artefacts and biases in the estimates, reinforcing the existence of a domain gap between simulation and experiment.