1 code implementation • 20 Nov 2023 • Julian Berberich, Daniel Fink, Daniel Pranjić, Christian Tutschku, Christian Holm
We derive tailored, parameter-dependent Lipschitz bounds for quantum models with trainable encoding, showing that the norm of the data encoding has a crucial impact on the robustness against perturbations in the input data.
no code implementations • 19 Oct 2023 • Julian Berberich, Daniel Fink
In particular, beyond the tutorial introduction, we provide a list of research challenges in the field of quantum computing and discuss their connections to control.
no code implementations • 27 Oct 2022 • Daniel Fink, Alison Johnston, Matt Strimas-Mackey, Tom Auer, Wesley M. Hochachka, Shawn Ligocki, Lauren Oldham Jaromczyk, Orin Robinson, Chris Wood, Steve Kelling, Amanda D. Rodewald
We used a simulation study to assess the ability of the method to estimate spatially varying trends in the face of real-world confounding.
no code implementations • 9 Mar 2021 • Wenting Zhao, Shufeng Kong, Junwen Bai, Daniel Fink, Carla Gomes
This in turn leads to a challenging and long-standing problem in the field of computer science - how to perform ac-curate multi-label classification with hundreds of labels?
no code implementations • 10 Mar 2018 • Hormoz Shahrzad, Daniel Fink, Risto Miikkulainen
An important benefit of multi-objective search is that it maintains a diverse population of candidates, which helps in deceptive problems in particular.
no code implementations • 28 Sep 2016 • Di Chen, Yexiang Xue, Shuo Chen, Daniel Fink, Carla Gomes
Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling.