Zobrazeno 1 - 10
of 118
pro vyhledávání: '"Petit, Maxime"'
Greedy algorithms for NLP such as transition based parsing are prone to error propagation. One way to overcome this problem is to allow the algorithm to backtrack and explore an alternative solution in cases where new evidence contradicts the solutio
Externí odkaz:
http://arxiv.org/abs/2206.13914
Autor:
Petit, Maxime, Weber-Delacroix, Eléonore, Lanthiez, François, Barthélémy, Sandrine, Guillou, Noëlline, Firpion, Marina, Bonduelle, Olivia, Hume, David A., Combadière, Christophe, Boissonnas, Alexandre
Publikováno v:
In Cell Reports 22 October 2024 43(10)
In robotics, methods and softwares usually require optimizations of hyperparameters in order to be efficient for specific tasks, for instance industrial bin-picking from homogeneous heaps of different objects. We present a developmental framework bas
Externí odkaz:
http://arxiv.org/abs/2007.15375
Publikováno v:
7th International Workshop on Image Analysis Methods in the Plant Sciences, Jul 2019, Lyon, France. pp.4 - 5
We propose a procedural fruit tree rendering framework, based on Blender and Python scripts allowing to generate quickly labeled dataset (i.e. including ground truth semantic segmentation). It is designed to train image analysis deep learning methods
Externí odkaz:
http://arxiv.org/abs/1907.04759
Publikováno v:
IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Sep 2018, Tokyo, Japan. 2018
We present a developmental framework based on a long-term memory and reasoning mechanisms (Vision Similarity and Bayesian Optimisation). This architecture allows a robot to optimize autonomously hyper-parameters that need to be tuned from any action
Externí odkaz:
http://arxiv.org/abs/1809.10141
Autor:
Moulin-Frier, Clément, Fischer, Tobias, Petit, Maxime, Pointeau, Grégoire, Puigbo, Jordi-Ysard, Pattacini, Ugo, Low, Sock Ching, Camilleri, Daniel, Nguyen, Phuong, Hoffmann, Matej, Chang, Hyung Jin, Zambelli, Martina, Mealier, Anne-Laure, Damianou, Andreas, Metta, Giorgio, Prescott, Tony J., Demiris, Yiannis, Dominey, Peter Ford, Verschure, Paul F. M. J.
Publikováno v:
IEEE Transactions on Cognitive and Developmental Systems 10 (4), 1005-1022, 2018
This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot. The framework, based
Externí odkaz:
http://arxiv.org/abs/1706.03661
Autor:
Petit, Maxime
Que cela soit par des automates puis par des robots, l'Homme a été fasciné par des machines pouvant exécuter des tâches pour lui, dans de nombreux domaines, comme l'industrie ou les services : c'est ce dernier domaine qui nous sert de contexte.
Externí odkaz:
http://www.theses.fr/2014LYO10037/document