Zobrazeno 1 - 7
of 7
pro vyhledávání: '"New, Zachary"'
Autor:
Lee, Jung H, Kvinge, Henry J, Howland, Scott, New, Zachary, Buckheit, John, Phillips, Lauren A., Skomski, Elliott, Hibler, Jessica, Corley, Courtney D., Hodas, Nathan O.
Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When TL is applied to DL, pretrained (teacher) models are fine-tuned to bu
Externí odkaz:
http://arxiv.org/abs/2111.10937
Autor:
Kvinge, Henry, Howland, Scott, Courts, Nico, Phillips, Lauren A., Buckheit, John, New, Zachary, Skomski, Elliott, Lee, Jung H., Tiwari, Sandeep, Hibler, Jessica, Corley, Courtney D., Hodas, Nathan O.
The field of few-shot learning has made remarkable strides in developing powerful models that can operate in the small data regime. Nearly all of these methods assume every unlabeled instance encountered will belong to a handful of known classes for
Externí odkaz:
http://arxiv.org/abs/2106.01423
Autor:
Skomski, Elliott, Tuor, Aaron, Avila, Andrew, Phillips, Lauren, New, Zachary, Kvinge, Henry, Corley, Courtney D., Hodas, Nathan
Recently proposed few-shot image classification methods have generally focused on use cases where the objects to be classified are the central subject of images. Despite success on benchmark vision datasets aligned with this use case, these methods t
Externí odkaz:
http://arxiv.org/abs/2104.03496
Autor:
Tymochko, Sarah, New, Zachary, Bynum, Lucius, Purvine, Emilie, Doster, Timothy, Chaput, Julien, Emerson, Tegan
Advances in natural language processing have resulted in increased capabilities with respect to multiple tasks. One of the possible causes of the observed performance gains is the introduction of increasingly sophisticated text representations. While
Externí odkaz:
http://arxiv.org/abs/2011.08952
Autor:
Kvinge, Henry, New, Zachary, Courts, Nico, Lee, Jung H., Phillips, Lauren A., Corley, Courtney D., Tuor, Aaron, Avila, Andrew, Hodas, Nathan O.
Deep learning has shown great success in settings with massive amounts of data but has struggled when data is limited. Few-shot learning algorithms, which seek to address this limitation, are designed to generalize well to new tasks with limited data
Externí odkaz:
http://arxiv.org/abs/2009.11253
Autor:
MING H. CHEN1, NEW, ZACHARY
Publikováno v:
Southern California Interdisciplinary Law Journal. Spring2019, Vol. 28 Issue 3, p549-587. 39p.
Autor:
NEW, ZACHARY
Publikováno v:
University of Colorado Law Review; Spring2022, Vol. 93 Issue 2, p367-403, 37p