Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Lee, Hyundo"'
Recent machine learning algorithms have been developed using well-curated datasets, which often require substantial cost and resources. On the other hand, the direct use of raw data often leads to overfitting towards frequently occurring class inform
Externí odkaz:
http://arxiv.org/abs/2402.08963
Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are difficult to access or interact with may be neglected throughout the c
Externí odkaz:
http://arxiv.org/abs/2305.13741
Understanding geometric concepts, such as distance and shape, is essential for understanding the real world and also for many vision tasks. To incorporate such information into a visual representation of a scene, we propose learning to represent the
Externí odkaz:
http://arxiv.org/abs/2304.08204
In Self-Supervised Learning (SSL), it is known that frequent occurrences of the collision in which target data and its negative samples share the same class can decrease performance. Especially in real-world data such as crawled data or robot-gathere
Externí odkaz:
http://arxiv.org/abs/2210.17052
Recently, adversarial imitation learning has shown a scalable reward acquisition method for inverse reinforcement learning (IRL) problems. However, estimated reward signals often become uncertain and fail to train a reliable statistical model since t
Externí odkaz:
http://arxiv.org/abs/2210.11201
Autor:
Kim, Taehyeong, Hwang, Injune, Lee, Hyundo, Kim, Hyunseo, Choi, Won-Seok, Lim, Joseph J., Zhang, Byoung-Tak
Active learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where data cannot be stored indefinitely due to limited storage or privacy
Externí odkaz:
http://arxiv.org/abs/2012.01227
We present an encoder-powered generative adversarial network (EncGAN) that is able to learn both the multi-manifold structure and the abstract features of data. Unlike the conventional decoder-based GANs, EncGAN uses an encoder to model the manifold
Externí odkaz:
http://arxiv.org/abs/1906.00541
Immiscible liquid-liquid displacement in microfluidic channels : effects of wettability and geometry
Autor:
Lee, Hyundo
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2017.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 153-174).
Displacement of a fluid by an immiscible flui
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 153-174).
Displacement of a fluid by an immiscible flui
Externí odkaz:
http://hdl.handle.net/1721.1/113544
Autor:
Choi, Jiwon1 (AUTHOR) edccjw@gmail.com, Lee, Hyundo1 (AUTHOR), Cho, Soyoung1 (AUTHOR), Choi, Yorim1 (AUTHOR), Pham, Thuy X.2 (AUTHOR), Huynh, Trang T. X.2 (AUTHOR), Lim, Yun-Sook2 (AUTHOR) yunsolim@hanmail.net, Hwang, Soon B.2,3 (AUTHOR)
Publikováno v:
Journal of Computer-Aided Molecular Design. Sep2023, Vol. 37 Issue 9, p453-461. 9p.
Autor:
Lee, Hyundo
Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2014.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 49-50).
Starting from unstructured glass microchannels, w
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 49-50).
Starting from unstructured glass microchannels, w
Externí odkaz:
http://hdl.handle.net/1721.1/92220