Zobrazeno 1 - 10
of 74
pro vyhledávání: '"Hodas, Nathan O"'
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:
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
Comprehensive and unambiguous identification of small molecules in complex samples will revolutionize our understanding of the role of metabolites in biological systems. Existing and emerging technologies have enabled measurement of chemical properti
Externí odkaz:
http://arxiv.org/abs/1905.08411
In this paper, we show that feedforward and recurrent neural networks exhibit an outer product derivative structure but that convolutional neural networks do not. This structure makes it possible to use higher-order information without needing approx
Externí odkaz:
http://arxiv.org/abs/1810.03798
Publikováno v:
J Comput Soc Sc (2018) 1: 295
In the modern knowledge economy, success demands sustained focus and high cognitive performance. Research suggests that human cognition is linked to a finite resource, and upon its depletion, cognitive functions such as self-control and decision-maki
Externí odkaz:
http://arxiv.org/abs/1809.02647
Autor:
Hodas, Nathan O., Stinis, Panos
As deep neural networks grow in size, from thousands to millions to billions of weights, the performance of those networks becomes limited by our ability to accurately train them. A common naive question arises: if we have a system with billions of d
Externí odkaz:
http://arxiv.org/abs/1805.04928
Autor:
Pirrung, Meg, Hilliard, Nathan, Yankov, Artëm, O'Brien, Nancy, Weidert, Paul, Corley, Courtney D, Hodas, Nathan O
Sharkzor is a web application for machine-learning assisted image sort and summary. Deep learning algorithms are leveraged to infer, augment, and automate the user's mental model. Initially, images uploaded by the user are spread out on a canvas. The
Externí odkaz:
http://arxiv.org/abs/1802.05316
Autor:
Hilliard, Nathan, Phillips, Lawrence, Howland, Scott, Yankov, Artëm, Corley, Courtney D., Hodas, Nathan O.
Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot tri
Externí odkaz:
http://arxiv.org/abs/1802.04376
With access to large datasets, deep neural networks (DNN) have achieved human-level accuracy in image and speech recognition tasks. However, in chemistry, data is inherently small and fragmented. In this work, we develop an approach of using rule-bas
Externí odkaz:
http://arxiv.org/abs/1712.02734