Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Kyong-Ha Lee"'
Autor:
Yu-Hee Kim, In Park, Soo Buem Cho, Seoyon Yang, Il Kim, Kyong-Ha Lee, Kwangnam Choi, Seung-Ho Han
Publikováno v:
Interactive Journal of Medical Research, Vol 12, p e48381 (2023)
Externí odkaz:
https://doaj.org/article/c66aba88638a4fcea6d918aee7919985
Publikováno v:
IEEE Access, Vol 9, Pp 68008-68016 (2021)
It is no longer an option but a necessity to enhance the efficiency of deep learning models regarding energy consumption, learning time, and model size as the computational burden on deep neural networks increases. To improve the efficiency of deep l
Externí odkaz:
https://doaj.org/article/55546893818a4be79f1380a26d03b689
Autor:
Eunhui Kim, Kyong-Ha Lee
Publikováno v:
IEEE Access, Vol 8, Pp 207683-207690 (2020)
Deep neural networks (DNN) have been applied to numerous artificial-intelligence applications because of their remarkable accuracy. However, computational requirements for deep neural networks are recently skyrocketing far beyond the Moore's Law. In
Externí odkaz:
https://doaj.org/article/465fa53d72214d2b9d5365361f5883a4
Publikováno v:
IEICE Transactions on Information and Systems. :551-555
Autor:
Kyong-Ha Lee, Eunhui Kim
Publikováno v:
IEEE Access, Vol 8, Pp 207683-207690 (2020)
Deep neural networks (DNN) have been applied to numerous artificial-intelligence applications because of their remarkable accuracy. However, computational requirements for deep neural networks are recently skyrocketing far beyond the Moore’s Law. I
Publikováno v:
Electronics, Vol 10, Iss 567, p 567 (2021)
Electronics
Volume 10
Issue 5
Electronics
Volume 10
Issue 5
To design an efficient deep learning model that can be used in the real-world, it is important to detect out-of-distribution (OOD) data well. Various studies have been conducted to solve the OOD problem. The current state-of-the-art approach uses a c
Publikováno v:
IEICE Transactions on Information and Systems. :1516-1520
Publikováno v:
The Journal of Supercomputing. 73:2339-2368
The multicore architecture has been the norm for all computing systems in recent years as it provides the CPU-level support of parallelism. However, existing algorithms for processing XML streams do not fully take advantage of the facility since they
Publikováno v:
The Journal of Supercomputing. 72:1312-1341
Modern block-oriented distributed storage systems like Hadoop distributed file system have proliferated in this era of big data and cloud computing. These systems feature block-level replication in which their files are partitioned into equal-sized b
Publikováno v:
Scientific Programming, Vol 2018 (2018)
Apache Hadoop has been a popular parallel processing tool in the era of big data. While practitioners have rewritten many conventional analysis algorithms to make them customized to Hadoop, the issue of inefficient I/O in Hadoop-based programs has be