Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Katz, Garrett"'
Due to the inherent lack of transparency in deep neural networks, it is challenging for deep reinforcement learning (DRL) agents to gain trust and acceptance from users, especially in safety-critical applications such as medical diagnosis and militar
Externí odkaz:
http://arxiv.org/abs/2411.16120
In robotic control tasks, policies trained by reinforcement learning (RL) in simulation often experience a performance drop when deployed on physical hardware, due to modeling error, measurement error, and unpredictable perturbations in the real worl
Externí odkaz:
http://arxiv.org/abs/2404.13879
Imitation learning allows social robots to learn new skills from human teachers without substantial manual programming, but it is difficult for robotic imitation learning systems to generalize demonstrated skills as well as human learners do. Contemp
Externí odkaz:
http://arxiv.org/abs/2211.06462
Autor:
Tahir, Naveed, Katz, Garrett E.
We present a computational method for empirically characterizing the training loss level-sets of deep neural networks. Our method numerically constructs a path in parameter space that is constrained to a set with a fixed near-zero training loss. By m
Externí odkaz:
http://arxiv.org/abs/2011.04189
Publikováno v:
In Neural Networks February 2022 146:200-219
Publikováno v:
In Neural Networks June 2021 138:78-97
Publikováno v:
In Neural Networks November 2019 119:10-30
Publikováno v:
Open Philosophy, Vol 2, Iss 1, Pp 252-269 (2019)
Recent advances in philosophical thinking about consciousness, such as cognitive phenomenology and mereological analysis, provide a framework that facilitates using computational models to explore issues surrounding the nature of consciousness. Here
Externí odkaz:
https://doaj.org/article/d5ec09242cec4910913f1ee299b94d68
Publikováno v:
In Neural Networks January 2017 85:165-181
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.