Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Andre Lemme"'
Publikováno v:
Neurocomputing. 141:3-14
The data-driven approximation of vector fields that encode dynamical systems is a persistently hard task in machine learning. If data is sparse and given in the form of velocities derived from few trajectories only, state-space regions exist, where n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a361a32795b6a146737f64dd565a12a4
https://doi.org/10.1016/j.neucom.2014.02.012
https://doi.org/10.1016/j.neucom.2014.02.012
Autor:
Andre Lemme, Andrea Soltoggio
Publikováno v:
International Journal of Automation and Computing. 10:375-386
Articulated movements are fundamental in many human and robotic tasks. While humans can learn and generalise arbitrarily long sequences of movements, and particularly can optimise them to fit the constraints and features of their body, robots are oft
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d2b64f2d0fb90309bfa598018af19fb
https://doi.org/10.1007/s11633-013-0734-9
https://doi.org/10.1007/s11633-013-0734-9
Publikováno v:
Neurocomputing. 112:179-188
Pointing at something refers to orienting the hand, the arm, the head or the body in the direction of an object or an event. This skill constitutes a basic communicative ability for cognitive agents like, e.g. humanoid robots. The goal of this study
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9503f61e9d025843e9510d29ced1123e
https://doi.org/10.1016/j.neucom.2012.12.040
https://doi.org/10.1016/j.neucom.2012.12.040
Publikováno v:
Neural Networks. 33:194-203
We present an efficient online learning scheme for non-negative sparse coding in autoencoder neural networks. It comprises a novel synaptic decay rule that ensures non-negative weights in combination with an intrinsic self-adaptation rule that optimi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c03449ef9a7c9aed530ac2d9bcc780a2
https://doi.org/10.1016/j.neunet.2012.05.003
https://doi.org/10.1016/j.neunet.2012.05.003
Autor:
Piotr Kwiatkowski, Alicja Sobczak, Krzysztof Kozłowski, Iwona Chwastowska-Siwiecka, Aleksandra Drażbo, Andre Lemme
Publikováno v:
European Poultry Science (EPS). 79
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::176d3fa8e4f0bb3aebd25e7c4135dc14
https://doi.org/10.1399/eps.2015.114
https://doi.org/10.1399/eps.2015.114
Autor:
Jochen J. Steil, Yaron Meirovitch, Seyed Mohammad Khansari-Zadeh, Andre Lemme, Tamar Flash, Aude Billard
Publikováno v:
Paladyn: Journal of Behavioral Robotics, Vol 6, Iss 1 (2015)
This paper introduces a benchmark framework to evaluate the performance of reaching motion generation approaches that learn from demonstrated examples. The system implements ten different performance measures for typical generalization tasks in robot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::df41b80000ad926ff1070dd968cbb4c8
https://doaj.org/article/db6bf670bf2c439a845de1584d69ffd6
https://doaj.org/article/db6bf670bf2c439a845de1584d69ffd6
Publikováno v:
Humanoids
Recent approaches have been advocated to learn a movement primitive library from demonstrations by using predefined motion features to identify and extract new movement primitives. In this paper, a new bootstrapping cycle is proposed which builds a s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::52e121678a583a8d21ec73d8ee5f8606
https://doi.org/10.1109/humanoids.2014.7041443
https://doi.org/10.1109/humanoids.2014.7041443
Autor:
Andre Lemme, Katharina J. Rohlfing, Maximilian Panzner, Sebastian Wrede, Philipp Cimiano, Judith Gaspers
Publikováno v:
PUB-Publications at Bielefeld University
This paper describes the design and acquisition of a German multimodal corpus for the development and evaluation of computational models for (grounded) language acquisition and algorithms enabling corresponding capabilities in robots. The corpus cont
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2eb35116a5923db7337b1e3eab91544
https://doi.org/10.3115/v1/w14-0507
https://doi.org/10.3115/v1/w14-0507
Publikováno v:
IROS
Nonlinear dynamical systems are a promising representation to learn complex robot movements. Besides their undoubted modeling power, it is of major importance that such systems work in a stable manner. We therefore present a neural learning scheme th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d5cc81af9ca63da1ea39068e6fae9bd3
https://doi.org/10.1109/iros.2013.6696505
https://doi.org/10.1109/iros.2013.6696505
Publikováno v:
ICDL-EPIROB
Learning in human-robot interaction, as well as in human-to-human situations, is characterised by noisy stimuli, variable timing of stimuli and actions, and delayed rewards. A recent model of neural learning, based on modulated plasticity, suggested
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff8c5ba53a0d9f51ac09861f0d50d602
https://pub.uni-bielefeld.de/record/2637629
https://pub.uni-bielefeld.de/record/2637629
