Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Oliver Lomp"'
Publikováno v:
Frontiers in Neurorobotics, Vol 11 (2017)
Handling objects or interacting with a human user about objects on a shared tabletop requires that objects be identified after learning from a small number of views and that object pose be estimated. We present a neurally inspired architecture that l
Externí odkaz:
https://doaj.org/article/610aba17972140c69e4276171b48c376
Publikováno v:
Frontiers in Neurorobotics, Vol 10 (2016)
Embodied artificial cognitive systems such as autonomous robots or intelligent observers connect cognitive processes to sensory and effector systems in real time. Prime candidates for such embodied intelligence are neurally inspired architectures. Wh
Externí odkaz:
https://doaj.org/article/5687a950daa84d88b42463ffd232b8e8
Publikováno v:
Frontiers in Neurorobotics
Frontiers in Neurorobotics, Vol 11 (2017)
Frontiers in Neurorobotics, Vol 11 (2017)
Handling objects or interacting with a human user about objects on a shared tabletop requires that objects be identified after learning from a small number of views and that object pose be estimated. We present a neurally inspired architecture that l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc17c7088bf7e7663fb301b9f76d78f8
https://doi.org/10.3389/fnbot.2017.00023
https://doi.org/10.3389/fnbot.2017.00023
Publikováno v:
Frontiers in Neurorobotics, Vol 10 (2016)
Frontiers in Neurorobotics
Frontiers in Neurorobotics
Embodied artificial cognitive systems, such as autonomous robots or intelligent observers, connect cognitive processes to sensory and effector systems in real time. Prime candidates for such embodied intelligence are neurally inspired architectures.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3fdcdf9d5be8cbc45ad88a83689f4f68
http://journal.frontiersin.org/Journal/10.3389/fnbot.2016.00014/full
http://journal.frontiersin.org/Journal/10.3389/fnbot.2016.00014/full
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2014 ISBN: 9783319111780
ICANN
ICANN
We present a method for biologically-inspired object recognition with one-shot learning of object appearance. We use a computationally efficient model of V1 keypoints to select object parts with the highest information content and model their surroun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1d3895f768b7107c8bed0a368812b326
https://doi.org/10.1007/978-3-319-11179-7_57
https://doi.org/10.1007/978-3-319-11179-7_57
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2013 ISBN: 9783642407277
ICANN
ICANN
We present Cedar, a software framework for the implementation and simulation of embodied cognitive models based on Dynamic Field Theory (DFT). DFT is a neurally inspired theoretical framework that integrates perception, action, and cognition. Cedar c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35d7dea8b23a4364a98ad2c59b109c77
https://doi.org/10.1007/978-3-642-40728-4_60
https://doi.org/10.1007/978-3-642-40728-4_60
Evolutionary optimization of growing neural gas parameters for object categorization and recognition
Publikováno v:
IJCNN
The already introduced Neural Map provides a structural association for the building blocks of dynamically generated object models. Its learning and recall procedures are built upon the Growing Neural Gas algorithm, which is highly parameterized. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b26b9a00d092c5e9f38b02504fb41f12
https://doi.org/10.1109/ijcnn.2010.5596682
https://doi.org/10.1109/ijcnn.2010.5596682