no code implementations • 9 Oct 2023 • Daniel Anthes, Sushrut Thorat, Peter König, Tim C. Kietzmann
Unlike primates, training artificial neural networks on changing data distributions leads to a rapid decrease in performance on old tasks.
no code implementations • 7 Oct 2023 • Daniel Anthes, Sushrut Thorat, Peter König, Tim C. Kietzmann
Continual learning algorithms strive to acquire new knowledge while preserving prior information.
1 code implementation • 3 Feb 2021 • Viviane Clay, Peter König, Gordon Pipa, Kai-Uwe Kühnberger
Following this, the representations learned through interaction with the world can be used to associate semantic concepts such as different types of doors.
no code implementations • 22 Dec 2020 • Farbod N. Nezami, Maximilian A. Wächter, Nora Maleki, Philipp Spaniol, Lea M. Kühne, Anke Haas, Johannes M. Pingel, Linus Tiemann, Frederik Nienhaus, Lynn Keller, Sabine König, Peter König, Gordon Pipa
The presented project contains all needed functionalities for realistic traffic behavior, cars, and pedestrians, as well as a large, open-source, scriptable, and modular VR environment.
Human-Computer Interaction
no code implementations • 25 Sep 2019 • Viviane Clay, Peter König, Kai-Uwe Kühnberger, Gordon Pipa
How do humans acquire a meaningful understanding of the world with little to no supervision or semantic labels provided by the environment?
no code implementations • 24 Sep 2019 • Peter König, Sandra Aigner, Marco Körner
This ensures the quality of the predicted frames to be sufficient to enable accurate detection of objects, which is especially important for autonomously driving cars.
no code implementations • 26 Jun 2019 • Alex Hernández-García, Peter König
As a matter of fact, convolutional neural networks for image object classification are typically trained with both data augmentation and explicit regularization, assuming the benefits of all techniques are complementary.
1 code implementation • 11 Jun 2019 • Alex Hernández-García, Peter König, Tim C. Kietzmann
Deep convolutional neural networks trained for image object categorization have shown remarkable similarities with representations found across the primate ventral visual stream.
2 code implementations • ICLR 2018 • Alex Hernández-García, Peter König
Despite the fact that some (explicit) regularization techniques, such as weight decay and dropout, require costly fine-tuning of sensitive hyperparameters, the interplay between them and other elements that provide implicit regularization is not well understood yet.
1 code implementation • 20 Feb 2018 • Alex Hernández-García, Peter König
The impressive success of modern deep neural networks on computer vision tasks has been achieved through models of very large capacity compared to the number of available training examples.