Výsledky vyhledávání - "Jeong, In cheol"

Report

ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate

Autor: Taniguchi, Shohei, Harada, Keno, Minegishi, Gouki, Oshima, Yuta, Jeong, Seong Cheol, Nagahara, Go, Iiyama, Tomoshi, Suzuki, Masahiro, Iwasawa, Yusuke, Matsuo, Yutaka

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\beta_2$, in a problem-dependent manner. There have been many attempts to fi

Externí odkaz: http://arxiv.org/abs/2411.02853

Zobrazit plný text záznamu

Report

BaRiFlex: A Robotic Gripper with Versatility and Collision Robustness for Robot Learning

Autor: Jeong, Gu-Cheol, Bahety, Arpit, Pedraza, Gabriel, Deshpande, Ashish D., Martín-Martín, Roberto

We present a new approach to robot hand design specifically suited for successfully implementing robot learning methods to accomplish tasks in daily human environments. We introduce BaRiFlex, an innovative gripper design that alleviates the issues ca

Externí odkaz: http://arxiv.org/abs/2312.05323

Zobrazit plný text záznamu