no code implementations • 21 Apr 2024 • Lukas D. Pöhler, Klaus Diepold, Wendell Wallach
This work presents a practical framework for multilevel governance of AIS.
no code implementations • 6 Feb 2024 • Sven Gronauer, Tom Haider, Felippe Schmoeller da Roza, Klaus Diepold
Reinforcement learning algorithms need exploration to learn.
no code implementations • 24 Nov 2023 • Stefan Röhrl, Johannes Groll, Manuel Lengl, Simon Schumann, Christian Klenk, Dominik Heim, Martin Knopp, Oliver Hayden, Klaus Diepold
Label-free approaches are attractive in cytological imaging due to their flexibility and cost efficiency.
no code implementations • 28 Sep 2022 • Yuqicheng Zhu, Mohamed-Ali Tnani, Timo Jahnz, Klaus Diepold
However, the learning efficiency strongly relies on the initial model, resulting in the trade-off between the size of the initial dataset and the query number.
no code implementations • 18 Aug 2022 • Stefan Röhrl, Alice Hein, Lucie Huang, Dominik Heim, Christian Klenk, Manuel Lengl, Martin Knopp, Nawal Hafez, Oliver Hayden, Klaus Diepold
As a direction for future research, we suggest a combination of Self-Organizing Maps and feature extraction based on deep learning.
1 code implementation • Procedia CIRP 2022 • Mohamed-Ali Tnani, Michael Feil, Klaus Diepold
To enhance the scalability of machine learning in real-world applications, this paper presents a benchmark dataset for process monitoring of brownfield milling machines based on acceleration data.
1 code implementation • 4 Jan 2022 • Sven Gronauer, Matthias Kissel, Luca Sacchetto, Mathias Korte, Klaus Diepold
In this work, we propose a data-driven approach to optimize the parameters of a simulation such that control policies can be directly transferred from simulation to a real-world quadrotor.
no code implementations • 16 Jun 2021 • Martin Gottwald, Sven Gronauer, Hao Shen, Klaus Diepold
First, we conduct a critical point analysis of the error function and provide technical insights on optimisation and design choices for neural networks.
no code implementations • 30 May 2019 • Johannes Günther, Elias Reichensdörfer, Patrick M. Pilarski, Klaus Diepold
In this paper, we examine the utility of extending PID controllers with recurrent neural networks-namely, General Dynamic Neural Networks (GDNN); we show that GDNN (neural) PID controllers perform well on a range of control systems and highlight how they can be a scalable and interpretable option for control systems.
no code implementations • 18 Mar 2019 • Michael Koller, Johannes Feldmaier, Klaus Diepold
This report first provides a brief overview of a number of supervised learning algorithms for regression tasks.
no code implementations • 27 Jun 2018 • Nicolas Berberich, Klaus Diepold
Modern AI and robotic systems are characterized by a high and ever-increasing level of autonomy.
no code implementations • 5 Oct 2016 • Dominik Meyer, Hao Shen, Klaus Diepold
In this paper, we study the Temporal Difference (TD) learning with linear value function approximation.
no code implementations • 24 Jun 2014 • Julian Habigt, Klaus Diepold
View synthesis is a process for generating novel views from a scene which has been recorded with a 3-D camera setup.
no code implementations • 24 Apr 2012 • Simon Hawe, Martin Kleinsteuber, Klaus Diepold
Our method is based on an $\ell_p$-norm minimization on the set of full rank matrices with normalized columns.