Zobrazeno 1 - 10
of 40
pro vyhledávání: '"German Ignacio Parisi"'
Autor:
Qihan Yang, Somesh Kumar, Qiaoyong Zhong, Fan Feng, Liang Ma, Qi She, Siew-Kei Lam, Gabriele Graffieti, German Ignacio Parisi, Yangsheng Xu, Baoquan Chen, Tin Lun Lam, Eoin Brophy, Chuanlin Lan, Vidit Goel, Lin Yang, Qi Liu, Rosa H. M. Chan, Debdoot Sheet, Shiliang Pu, Di Xie, Lorenzo Pellegrini, Hyonyoung Han, Liguang Zhou, Vincenzo Lomonaco, Zhengwei Wang, Soonyong Song, Davide Maltoni, Heechul Bae, Jianwen Wu, Xinyue Hao, Tomas E. Ward, Duvindu Piyasena, Sathursan Kanagarajah, Meiqing Wu, Young-Sung Son
Publikováno v:
IEEE Robotics & Automation Magazine. 27:11-16
Humans have a remarkable ability to learn continuously from th e environment and inner experience. One of the grand goals of robots is to build an artificial "lifelong learning" agent that can shape a cultivated understanding of the world from the cu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::26ea5e8210ef6c78f2ba2436e0e0d4c1
https://doi.org/10.1109/mra.2020.2987186
https://doi.org/10.1109/mra.2020.2987186
Publikováno v:
Frontiers in Neurorobotics, Vol 9 (2015)
The visual recognition of complex, articulated human movements is fundamental for a wide range of artificial systems oriented towards human-robot communication, action classification, and action-driven perception. These challenging tasks may generall
Externí odkaz:
https://doaj.org/article/3a083d6b1ffb48d9b0cc44f3f1b5f4e9
Publikováno v:
Neural Networks. 113:54-71
Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d50f8f27cb5e9ec092633d26100d9557
https://doi.org/10.1016/j.neunet.2019.01.012
https://doi.org/10.1016/j.neunet.2019.01.012
Publikováno v:
IEEE Transactions on Cognitive and Developmental Systems. 10:918-928
During visuomotor tasks, robots must compensate for temporal delays inherent in their sensorimotor processing systems. Delay compensation becomes crucial in a dynamic environment where the visual input is constantly changing, e.g., during the interac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd26e3a7d3f7bfa7ea946442ef50612a
https://doi.org/10.1109/tcds.2018.2832844
https://doi.org/10.1109/tcds.2018.2832844
Autor:
Aditi Ramachandran, Sinan Kalkan, Bahar Irfan, German Ignacio Parisi, Samuel Spaulding, Hatice Gunes
Publikováno v:
HRI (Companion)
While most of the research in Human-Robot Interaction (HRI) focuses on short-term interactions, long-term interactions require bolder developments and a substantial amount of resources, especially if the robots are deployed in the wild. Robots need t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::64dcf25e2d3f737806244c391f9d1795
https://doi.org/10.1145/3434074.3444881
https://doi.org/10.1145/3434074.3444881
Autor:
Simone Scardapane, Martin Mundt, Tyler L. Hayes, Simone Calderara, Keiland W. Cooper, Christopher Kanan, Eden Belouadah, Lorenzo Pellegrini, Adrian Popescu, Matthias De Lange, Fabio Cuzzolin, Jeremy Forest, Jary Pomponi, Subutai Ahmad, Qi She, Luca Antiga, Gido M. van de Ven, Davide Maltoni, Davide Bacciu, Vincenzo Lomonaco, Joost van de Weijer, Marc Masana, Antonio Carta, Gabriele Graffieti, Andreas S. Tolias, German Ignacio Parisi, Andrea Cossu, Tinne Tuytelaars
Publikováno v:
CVPR Workshops
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d293de3db110ff7791c5e28c4027ea01
http://hdl.handle.net/11573/1612489
http://hdl.handle.net/11573/1612489
Autor:
German Ignacio Parisi
Publikováno v:
Modelling Human Motion ISBN: 9783030467319
The robust recognition and assessment of human actions are crucial in human-robot interaction (HRI) domains. While state-of-the-art models of action perception show remarkable results in large-scale action datasets, they mostly lack the flexibility,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::69eea10f2c0fb820380b53cf7cbafa20
https://doi.org/10.1007/978-3-030-46732-6_10
https://doi.org/10.1007/978-3-030-46732-6_10
Publikováno v:
Recent Trends in Learning From Data ISBN: 9783030438821
Online continual learning (OCL) refers to the ability of a system to learn over time from a continuous stream of data without having to revisit previously encountered training samples. Learning continually in a single data pass is crucial for agents
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9298950555d11aab354406f6ca5c5dde
https://doi.org/10.1007/978-3-030-43883-8_8
https://doi.org/10.1007/978-3-030-43883-8_8
Autor:
Marc Pickett, Zheda Mai, German Ignacio Parisi, Davide Maltoni, Quentin Jodelet, Massimo Caccia, Nikhil Churamani, Qi She, Lorenzo Pellegrini, Yu Chen, Issam H. Laradji, Vincenzo Lomonaco, Pau Rodríguez, Ruiping Wang, David Vazquez
Publikováno v:
Artificial Intelligence. 303:103635
In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous. However, despite the signific
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38796e4705b92946c33032bd6155c5b4
https://doi.org/10.1016/j.artint.2021.103635
https://doi.org/10.1016/j.artint.2021.103635
Publikováno v:
Frontiers in Robotics and AI, Vol 6 (2019)
Frontiers in Robotics and AI
Frontiers in Robotics and AI
Expectation learning is an unsupervised learning process which uses multisensory bindings to enhance unisensory perception. For instance, as humans, we learn to associate a barking sound with the visual appearance of a dog, and we continuously fine-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8cef0cbfd9bc99871cf7a5d23f25aa17
https://doi.org/10.3389/frobt.2019.00137
https://doi.org/10.3389/frobt.2019.00137