Zobrazeno 1 - 10
of 89
pro vyhledávání: '"Andrei Barbu"'
Publikováno v:
Frontiers in Robotics and AI, Vol 8 (2021)
We demonstrate how a reinforcement learning agent can use compositional recurrent neural networks to learn to carry out commands specified in linear temporal logic (LTL). Our approach takes as input an LTL formula, structures a deep network according
Externí odkaz:
https://doaj.org/article/792344fe5b8b4886991fdf71deeb5aef
Publikováno v:
Pattern Recognition Letters. 137:99-107
We demonstrate how to construct a new class of visual assistive technologies that, rather than extract symbolic information, learn to transform the visual environment to make it more accessible. We do so without engineering which transformations are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d39bdb2a4234c32e4cac3720e3299d5
https://doi.org/10.1016/j.patrec.2019.01.019
https://doi.org/10.1016/j.patrec.2019.01.019
Publikováno v:
Annals: Series on engineering sciences (Academy of Romanian Scientists), Vol 3, Iss 1, Pp 15-22 (2011)
Vibrations influence the human body in many different ways. The response to a vibration exposure is primarily dependent on the frequency, amplitude, and duration of exposure. This paper studies the influence of vibrations generated by automobiles on
Externí odkaz:
https://doaj.org/article/a2281429788143d4bd6192b6f96f3f9b
Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained on that dat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aeb8289274b1939f96139705af510265
http://arxiv.org/abs/2110.07575
http://arxiv.org/abs/2110.07575
How well do deep neural networks fare as models of mouse visual cortex? A majority of research to date suggests results far more mixed than those produced in the modeling of primate visual cortex. Here, we perform a large-scale benchmarking of dozens
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::86e1852d1b990a71b8a8df52f3ad7616
https://doi.org/10.1101/2021.06.18.448431
https://doi.org/10.1101/2021.06.18.448431
Autor:
Ionut Andrei Barbu
Publikováno v:
EIRP Proceedings, Vol 3, Iss 1, Pp 233-235 (2008)
În doctrina dreptului internaţional există păreri bine fundamentate care refuză să accepte teoriaconform căreia individul ar avea calitatea de subiect de drept internaţional.Astfel, unii autori consideră că persoanele fizice, chiar dacă au
Externí odkaz:
https://doaj.org/article/03e11c9dcf6543beaff13edaae47f8aa
Publikováno v:
Dreptul; 2018, Issue 2, p158-166, 9p
Publikováno v:
SeeNews Research & Profiles (Company Profiles). 2012, p6169-6174. 6p.
Publikováno v:
IROS
We demonstrate a reinforcement learning agent which uses a compositional recurrent neural network that takes as input an LTL formula and determines satisfying actions. The input LTL formulas have never been seen before, yet the network performs zero-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9acb2d890d5761885f7c288b6c50c869
http://arxiv.org/abs/2006.01110
http://arxiv.org/abs/2006.01110
Publikováno v:
ICRA
We demonstrate how a sampling-based robotic planner can be augmented to learn to understand a sequence of natural language commands in a continuous configuration space to move and manipulate objects. Our approach combines a deep network structured ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e01f46e039cf967b27c6e5f0bda7c38