Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Takashi Hasuo"'
Publikováno v:
The International Journal of Robotics Research. 27:373-386
A new prototype of a self-reconfigurable modular robot, M-TRAN III, has been developed, with an improved fast and rigid connection mechanism. Using a distributed controller, various control modes are possible: single-master, globally synchronous cont
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb3ff26ad588b090520ff8237e49d46b
https://doi.org/10.1177/0278364907085560
https://doi.org/10.1177/0278364907085560
Publikováno v:
ICDL-EPIROB
By manipulating objects in their environment, infants learn about the surrounding environment and continuously improve their internal model of their own body. Moreover, infants learn to distinguish parts of their own body from other objects in the en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::141b1192c6f4f8908a58faf159b282e8
https://doi.org/10.1109/devlrn.2011.6037357
https://doi.org/10.1109/devlrn.2011.6037357
Publikováno v:
ICDL-EPIROB
Human infants learn to interpret their visuomotor experience and predict the effects of their actions by practicing interactions with the environment. This paper presents a computational model of this process that can be implemented in an artificial
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6830c83734051ddf4534d8ac93ae3943
https://doi.org/10.1109/devlrn.2011.6037362
https://doi.org/10.1109/devlrn.2011.6037362
Publikováno v:
Advances in Cognitive Neurodynamics ICCN 2007 ISBN: 9781402083860
Dynamics of traditional neural network models are generally time-invari-ant. For that reason, they have limitations in context-dependent processing. We present a new method, dynamic desensitization, of varying neurodynamics continuously and construct
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4693376fcee1f97e7e022495a9bb8990
https://doi.org/10.1007/978-1-4020-8387-7_41
https://doi.org/10.1007/978-1-4020-8387-7_41
Publikováno v:
Neural Information Processing ISBN: 9783540691594
ICONIP (2)
ICONIP (2)
It is considered that a key to overcoming the limitations of classical artificial intelligence is to process distributed representations of information without symbolizing them. However, conventional neural networks require local or symbolic represen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0df7967714ff15344c11a2df7d9154a5
https://doi.org/10.1007/978-3-540-69162-4_111
https://doi.org/10.1007/978-3-540-69162-4_111
Autor:
Haruhisa Kurokawa, Kohji Tomita, Akiya Kamimura, Shigeru Kokaji, Takashi Hasuo, Satoshi Murata
Publikováno v:
The Proceedings of First International Conference on Robot Communication and Coordination.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::573f4d4b964113f880b76b875a009a6b
https://doi.org/10.4108/icst.robocomm2007.2119
https://doi.org/10.4108/icst.robocomm2007.2119