Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Jan Hendrik Metzen"'
Autor:
Lisa Gutzeit, Alexander Fabisch, Marc Otto, Jan Hendrik Metzen, Jonas Hansen, Frank Kirchner, Elsa Andrea Kirchner
Publikováno v:
Frontiers in Robotics and AI, Vol 5 (2018)
We describe the BesMan learning platform which allows learning robotic manipulation behavior. It is a stand-alone solution which can be combined with different robotic systems and applications. Behavior that is adaptive to task changes and different
Externí odkaz:
https://doaj.org/article/8e0a6d45bb934793adf231fdf5e1085e
Autor:
Mario Michael Krell, Sirko eStraube, Anett eSeeland, Hendrik eWöhrle, Johannes eTeiwes, Jan Hendrik Metzen, Elsa Andrea Kirchner, Frank eKirchner
Publikováno v:
Frontiers in Neuroinformatics, Vol 7 (2013)
In neuroscience large amounts of data are recorded to provide insights into cerebral information processing and function. The successful extraction of the relevant signals becomes more and more challenging due to increasing complexities in acquisitio
Externí odkaz:
https://doaj.org/article/0ffdd9f039254bf68f1a2798ee780a99
Autor:
Jan Hendrik Metzen, Frank eKirchner
Publikováno v:
Frontiers in Neurorobotics, Vol 7 (2013)
Life-long learning of reusable, versatile skills is a key prerequisite forembodied agents that act in a complex, dynamic environment and are faced withdifferent tasks over their lifetime. We address the question of how an agentcan learn useful skills
Externí odkaz:
https://doaj.org/article/7973510a45ca4e34ae3270de280904f7
Autor:
Rohit Mohan, Thomas Elsken, Arber Zela, Jan Hendrik Metzen, Benedikt Staffler, Thomas Brox, Abhinav Valada, Frank Hutter
Publikováno v:
International Journal of Computer Vision.
The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering. As a consequence, neural architecture search (NAS), which aims at automatically designing neural network architectures in a data-dri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::93746da8f0309595fd05b1aea82f624e
https://doi.org/10.1007/s11263-023-01785-y
https://doi.org/10.1007/s11263-023-01785-y
Autor:
Giulio Lovisotto, Nicole Finnie, Mauricio Munoz, Chaithanya Kumar Murnmadi, Jan Hendrik Metzen
Neural architectures based on attention such as vision transformers are revolutionizing image recognition. Their main benefit is that attention allows reasoning about all parts of a scene jointly. In this paper, we show how the global reasoning of (s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ba2b68191a89f5ba1ec1499937e49346
Publikováno v:
CVPR
The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the application of NAS a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::429a97ffb557be82611ae479034bd4ba
http://arxiv.org/abs/1911.11090
http://arxiv.org/abs/1911.11090
Publikováno v:
Automated Machine Learning ISBN: 9783030053178
Automated Machine Learning
Automated Machine Learning
Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aca234484b5b9bebc7ef95b3da90550a
https://doi.org/10.1007/978-3-030-05318-5_3
https://doi.org/10.1007/978-3-030-05318-5_3
Publikováno v:
Automated Machine Learning ISBN: 9783030053178
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b7b5da7facd506eabc9c254a2318446
https://doi.org/10.1007/978-3-030-05318-5_11
https://doi.org/10.1007/978-3-030-05318-5_11
Publikováno v:
ICCV
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image classifiers against such adversaria
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f7233c95bc5e130f825a311caab4af6
http://arxiv.org/abs/1812.03705
http://arxiv.org/abs/1812.03705
Publikováno v:
KI - Künstliche Intelligenz. 29:369-377
Contextual policy search is a reinforcement learning approach for multi-task learning in the context of robot control learning. It can be used to learn versatilely applicable skills that generalize over a range of tasks specified by a context vector.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::835f36af7a9adb38f47925ac83dad6ad
https://doi.org/10.1007/s13218-015-0363-2
https://doi.org/10.1007/s13218-015-0363-2