Asymmetric Momentum: A Rethinking of Gradient Descent

Autor: Zhang, Gongyue, Zhang, Dinghuang, Zhao, Shuwen, Liu, Donghan, Toptan, Carrie M., Liu, Honghai

Through theoretical and experimental validation, unlike all existing adaptive methods like Adam which penalize frequently-changing parameters and are only applicable to sparse gradients, we propose the simplest SGD enhanced method, Loss-Controlled As

Externí odkaz: http://arxiv.org/abs/2309.02130

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

An intuitive robot learning from human demonstration

Autor: Ogenyi, Uchenna Emeoha, Zhang, Gongyue, Yang, Chenguang, Ju, Zhaojie, Liu, Honghai

Publikováno v: Ogenyi, U E, Zhang, G, Yang, C, Ju, Z & Liu, H 2018, An intuitive robot learning from human demonstration . in Z Chen, A Mendes, Y Yan & S Chen (eds), Intelligent Robotics and Applications : 11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9–11, 2018, Proceedings, Part I . Lecture Notes in Computer Science, vol. 10984, Springer, pp. 176-185, 11th International Conference on Intelligent Robotics and Applications, Newcastle, Australia, 9/08/18 . https://doi.org/10.1007/978-3-319-97586-3_16

This paper presents a new way to teach a robot certain motions remotely from human demonstrator. The human and robot interface is built using a Kinect sensor which is connected directly to a remote computer that runs on processing software. The Carte

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3461::01fbeb0e15a263e9ae86e0f049b2c486
https://researchportal.port.ac.uk/portal/en/publications/an-intuitive-robot-learning-from-human-demonstration(fdec9e86-0b5b-4e7e-b3f7-b3568657016b).html