Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Daucé, Emmanuel"'
Foveated vision, a trait shared by many animals, including humans, has not been fully utilized in machine learning applications, despite its significant contributions to biological visual function. This study investigates whether retinotopic mapping,
Externí odkaz:
http://arxiv.org/abs/2402.15480
Autor:
Daucé, Emmanuel
The capability to widely sample the state and action spaces is a key ingredient toward building effective reinforcement learning algorithms. The variational optimization principles exposed in this paper emphasize the importance of an occupancy model
Externí odkaz:
http://arxiv.org/abs/2205.12020
Autor:
Daucé, Emmanuel
Stemming on the idea that a key objective in reinforcement learning is to invert a target distribution of effects, end-effect drives are proposed as an effective way to implement goal-directed motor learning, in the absence of an explicit forward mod
Externí odkaz:
http://arxiv.org/abs/2006.15960
Autor:
Daucé, Emmanuel
We develop a comprehensive description of the active inference framework, as proposed by Friston (2010), under a machine-learning compliant perspective. Stemming from a biological inspiration and the auto-encoding principles, the sketch of a cognitiv
Externí odkaz:
http://arxiv.org/abs/1710.10460
Autor:
Daucé, Emmanuel
The objective of this dissertation is to shed light on some fundamental impediments in learning control laws in continuous state spaces. In particular, if one wants to build artificial devices capable to learn motor tasks the same way they learn to c
Externí odkaz:
http://arxiv.org/abs/1609.09681
Publikováno v:
Journal of Vision
Journal of Vision, Association for Research in Vision and Ophthalmology, 2020, 20 (8), pp.22. ⟨10.1167/jov.20.8.22⟩
Journal of Vision, 2020, 20 (8), pp.22. ⟨10.1167/jov.20.8.22⟩
Journal of Vision, Association for Research in Vision and Ophthalmology, 2020, 20 (8), pp.22. ⟨10.1167/jov.20.8.22⟩
Journal of Vision, 2020, 20 (8), pp.22. ⟨10.1167/jov.20.8.22⟩
Visual search involves a dual task of localizing and categorizing an object in the visual field of view. We develop a visuo-motor model that implements visual search as a focal accuracy-seeking policy, and we assume that the target position and categ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e5b45dfe5d92faf8bb289daed8ab6251
https://hal-amu.archives-ouvertes.fr/hal-02947410/file/i1534-7362-20-8-22_1597915038.46867.pdf
https://hal-amu.archives-ouvertes.fr/hal-02947410/file/i1534-7362-20-8-22_1597915038.46867.pdf
Publikováno v:
In Neurocomputing 2007 70(10):2009-2016
Autor:
Daucé Emmanuel, Malhotra Gaurav
Publikováno v:
BMC Neuroscience, Vol 12, Iss Suppl 1, p P53 (2011)
Externí odkaz:
https://doaj.org/article/a9e15302dc7042fdb83e83beeee3b1b3
Publikováno v:
BMC Neuroscience, Vol 12, Iss Suppl 1, p P133 (2011)
Externí odkaz:
https://doaj.org/article/bb92b65b804a407b9f51d89e98da8c84
Autor:
Zhong, Hongliang, Daucé, Emmanuel
The bandit classification problem considers learning the labels of a time-indexed data stream under a mere " hit-or-miss " binary guiding. Adapting the OVA (" one-versus-all ") hinge loss setup, we develop a sparse and lightweight solution to this pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::31b5569f0cbbd8cf07b7eeedcae0cf6e
https://hal.archives-ouvertes.fr/hal-01345825
https://hal.archives-ouvertes.fr/hal-01345825