Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Luciw Matthew"'
Publikováno v:
Paladyn, Vol 6, Iss 1 (2015)
In order to proceed along an action sequence, an autonomous agent has to recognize that the intended final condition of the previous action has been achieved. In previous work, we have shown how a sequence of actions can be generated by an embodied a
Externí odkaz:
https://doaj.org/article/0e54079367cd4722bceb12c190811a7d
Autor:
Weng Juyang, Luciw Matthew D
Publikováno v:
BMC Neuroscience, Vol 11, Iss Suppl 1, p P83 (2010)
Externí odkaz:
https://doaj.org/article/45980bf63488455db40151c62a36d766
Autor:
Weng Juyang, Luciw Matthew D
Publikováno v:
BMC Neuroscience, Vol 11, Iss Suppl 1, p P132 (2010)
Externí odkaz:
https://doaj.org/article/4baed0e97c4e4f14ba65e4f418a9b674
We introduce a dynamic neural algorithm called Dynamic Neural (DN) SARSA(\lambda) for learning a behavioral sequence from delayed reward. DN-SARSA(\lambda) combines Dynamic Field Theory models of behavioral sequence representation, classical reinforc
Externí odkaz:
http://arxiv.org/abs/1210.3569
Publikováno v:
Neural Computation, 2012, Vol. 24, No. 11, Pages 2994-3024
Slow Feature Analysis (SFA) extracts features representing the underlying causes of changes within a temporally coherent high-dimensional raw sensory input signal. Our novel incremental version of SFA (IncSFA) combines incremental Principal Component
Externí odkaz:
http://arxiv.org/abs/1112.2113
Publikováno v:
In Artificial Intelligence June 2017 247:313-335
Autor:
Wong, Andy, Jazi, Mehran Taghian, Takeuchi, Tomoharu, Günther, Johannes, Zaïane, Osmar, Luciw, Matthew David, Silva, Eliana Oliveira Da Costa E.
Publikováno v:
Frontiers in Robotics & AI; 2024, p1-12, 12p
Autor:
Kompella, Varun Raj1 varunrajk@gmail.com, Luciw, Matthew1 luciwmat@gmail.com, Stollenga, Marijn Frederik1 marijn@idsia.ch, Schmidhuber, Juergen1 juergen@idsia.ch
Publikováno v:
Neural Computation. 2016, Vol. 28 Issue 8, p1599-1662. 64p. 6 Diagrams, 1 Chart, 9 Graphs.
Autor:
Kompella, Varun Raj1 varun@idsia.ch, Luciw, Matthew1 matthew@idsia.ch, Schmidhuber, Jürgen1 juergen@idsia.ch
Publikováno v:
Neural Computation. Nov2012, Vol. 24 Issue 11, p2994-3024. 31p. 2 Diagrams, 8 Graphs.
Artificial curiosity tries to maximize learning progress. We apply this concept to a physical system. Our Katana robot arm curiously plays with wooden blocks, using vision, reaching, and grasping. It is intrinsically motivated to explore its world. A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2659::502e31d05493d3d74d45fe88e9aab39f
https://zenodo.org/record/1273451
https://zenodo.org/record/1273451