Search

Your search keyword '"Sohn, So Young"' showing total 1,432 results
Start Over Author "Sohn, So Young"
1,432 results on '"Sohn, So Young"'

6. Understanding Dynamic Spatio-Temporal Contexts in Long Short-Term Memory for Road Traffic Speed Prediction

Author

Lee, Won Kyung, Kwon, Deuk Sin, and Sohn, So Young

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Reliable traffic flow prediction is crucial to creating intelligent transportation systems. Many big-data-based prediction approaches have been developed but they do not reflect complicated dynamic interactions between roads considering time and location. In this study, we propose a dynamically localised long short-term memory (LSTM) model that involves both spatial and temporal dependence between roads. To do so, we use a localised dynamic spatial weight matrix along with its dynamic variation. Moreover, the LSTM model can deal with sequential data with long dependency as well as complex non-linear features. Empirical results indicated superior prediction performances of the proposed model compared to two different baseline methods., Comment: 10pages, 2 tables, 4 figures, 2017 KDD Cup

Published
2021

16. LazyTensor: combining eager execution with domain-specific compilers

Author

Suhan, Alex, Libenzi, Davide, Zhang, Ailing, Schuh, Parker, Saeta, Brennan, Sohn, Jie Young, and Shabalin, Denys

Subjects
Computer Science - Programming Languages, Computer Science - Machine Learning
Abstract

Domain-specific optimizing compilers have demonstrated significant performance and portability benefits, but require programs to be represented in their specialized IRs. Existing frontends to these compilers suffer from the "language subset problem" where some host language features are unsupported in the subset of the user's program that interacts with the domain-specific compiler. By contrast, define-by-run ML frameworks-colloquially called "eager" mode-are popular due to their ease of use and expressivity, where the full power of the host programming language can be used. LazyTensor is a technique to target domain specific compilers without sacrificing define-by-run ergonomics. Initially developed to support PyTorch on Cloud TPUs, the technique, along with a substantially shared implementation, has been used by Swift for TensorFlow across CPUs, GPUs, and TPUs, demonstrating the generality of the approach across (1) Tensor implementations, (2) hardware accelerators, and (3) programming languages.

Published
2021

25. Correction for Nebenzahl-Sharon et al., “An Interaction with PARP-1 and Inhibition of Parylation Contribute to Attenuation of DNA Damage Signaling by the Adenovirus E4orf4 Protein”

Author

Nebenzahl-Sharon, Keren, primary, Sharf, Rakefet, additional, Amer, Jana, additional, Shalata, Hassan, additional, Khoury-Haddad, Hanan, additional, Sohn, Sook-Young, additional, Ayoub, Nabieh, additional, Hearing, Patrick, additional, and Kleinberger, Tamar, additional

Published
2024
Full Text
View/download PDF

35. A firm's creation of proprietary knowledge linked to the knowledge spilled over from its research publications: the case of artificial intelligence.

Author

Jee, Su Jung and Sohn, So Young

Subjects
ARTIFICIAL intelligence, PAPER industry, BUSINESS enterprises
Abstract

This study investigates the mechanism by which knowledge spilled over from a firm's research publication consequently spills into the focal firm as a form of proprietary knowledge when it is engaged in an emerging science-related technology. We define the knowledge spillover pool (KSP) as an evolving group of papers citing a paper published by a firm. Focusing on the recent development of artificial intelligence, on which firms have published actively, we compare the KSP conditions related to the increase in patents created by the focal firm with those created by external actors. Using a Cox regression and subsequent contrast test, we find that both an increasing KSP and an increasing similarity between the idea published by the focal firm and KSP are positively related to the proprietary knowledge creation of both the focal firm and external actors, with such relations being significantly stronger for the focal firm than for external actors. On the contrary, an increasing proportion of industry papers in the KSP are positively associated with the proprietary knowledge creation not only by the focal firm but also by external actors to a similar degree. We contribute to the literature on selective revealing and to the firms' publishing strategies. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

37. Restrained and Total Restrained Domination in Cographs

Author

Chen, Xue-gang, Sohn, Moo Young, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Wu, Weili, editor, and Du, Hongwei, editor

Published
2021
Full Text
View/download PDF

38. Cosmetic patent and female invention.

Author

Lee, Jong Wook, Jeon, Eunji, and Sohn, So Young

Subjects
PATENT offices, PATENT applications, POISSON regression, GENDER inequality, SURVIVAL analysis (Biometry)
Abstract

Majority customers of cosmetics are female. Would this imply a high proportion of inventors of cosmetics technology is female? Would the inventor's gender be related to the characteristics and quality of corresponding patent? This study tries to identify manifestation of gender equity in cosmetics technology in terms of patent application and grant, technical characteristics, and its performance. We apply topic modeling, zero-inflated Poisson regression, and survival analysis to patents related to cosmetics that were applied to the United States Patent and Trademark Office from 1970 to 2016. The results show that women's participation in cosmetic inventions is becoming active and has experienced many changes in technical characteristics, but in terms of performance, it is still sluggish. This study is expected to contribute to deepening our understanding about gender issues in technology development. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results