no code implementations • 18 Jan 2024 • Jill Baumann, Oliver Kramer
In this work, we propose a evolutionary multi-objective (EMO) approach specifically tailored for prompt optimization called EMO-Prompts, using sentiment analysis as a case study.
no code implementations • 27 Oct 2021 • Stefan Böhm, Martin Neumayer, Oliver Kramer, Alexander Schiendorfer, Alois Knoll
Cutting and Packing problems are occurring in different industries with a direct impact on the revenue of businesses.
no code implementations • 3 Jun 2020 • Lars Elend, Sebastian A. Tideman, Kerstin Lopatta, Oliver Kramer
In the financial sector, a reliable forecast the future financial performance of a company is of great importance for investors' investment decisions.
no code implementations • 6 May 2020 • Tim Cofala, Lars Elend, Philip Mirbach, Jonas Prellberg, Thomas Teusch, Oliver Kramer
Computational drug design based on artificial intelligence is an emerging research area.
1 code implementation • 23 Mar 2020 • Jonas Prellberg, Oliver Kramer
In deep multi-task learning, weights of task-specific networks are shared between tasks to improve performance on each single one.
1 code implementation • 21 Jun 2019 • Jonas Prellberg, Oliver Kramer
Examining blood microscopic images for leukemia is necessary when expensive equipment for flow cytometry is unavailable.
1 code implementation • 26 Jun 2018 • Jonas Prellberg, Oliver Kramer
Finally, we train a network with 92k parameters on MNIST using an EA and achieve 97. 6 % test accuracy compared to 98 % test accuracy on the same network trained with Adam.
no code implementations • 21 Jun 2018 • Jonas Prellberg, Oliver Kramer
Convolutional neural networks belong to the most successul image classifiers, but the adaptation of their network architecture to a particular problem is computationally expensive.
no code implementations • 15 May 2018 • Jonas Prellberg, Oliver Kramer
Automatic tool detection from surgical imagery has a multitude of useful applications, such as real-time computer assistance for the surgeon.
no code implementations • 11 Sep 2017 • Oliver Kramer
Convolutional highways are deep networks based on multiple stacked convolutional layers for feature preprocessing.