Zobrazeno 1 - 10 of 26 pro vyhledávání: '"Chang Ho Ryu"'
1
Akademický článek
Deep learning-based material decomposition of iodine and calcium in mobile photon counting detector CT.
Autor: Kwanhee Han, Chang Ho Ryu, Chang-Lae Lee, Tae Hee Han
Publikováno v: PLoS ONE, Vol 19, Iss 7, p e0306627 (2024)
Photon-counting detector (PCD)-based computed tomography (CT) offers several advantages over conventional energy-integrating detector-based CT. Among them, the ability to discriminate energy exhibits significant potential for clinical applications be
Externí odkaz: https://doaj.org/article/1425ab7931724cc78714388f7d58b4d8
Zobrazit plný text záznamu
2
Akademický článek
SFAO: Sign-Flipping-Aware Optimization for Early-Stopping of Binarized Neural Networks
Autor: Ju Yeon Kang, Chang Ho Ryu, Suk Bong Kang, Tae Hee Han
Publikováno v: IEEE Access, Vol 11, Pp 128306-128315 (2023)
One of the vital challenges for the binary neural networks (BNNs) is improving their inference performance by expanding their data representation capabilities for figuring out delicate patterns and nuances in the data. Addressing the explosive comput
Externí odkaz: https://doaj.org/article/3fe4fb2a469f4be88a09a8c44c201de1
Zobrazit plný text záznamu
3
Akademický článek
Binarized Neural Network With Parameterized Weight Clipping and Quantization Gap Minimization for Online Knowledge Distillation
Autor: Ju Yeon Kang, Chang Ho Ryu, Tae Hee Han
Publikováno v: IEEE Access, Vol 11, Pp 8057-8064 (2023)
As the applications for artificial intelligence are growing rapidly, numerous network compression algorithms have been developed to restrict computing resources such as smartphones, edge, and IoT devices. Knowledge distillation (KD) leverages soft la
Externí odkaz: https://doaj.org/article/f9e9e24052ce4c27b99dd7a27f6068fe
Zobrazit plný text záznamu
5
CSGN: Combined Channel- and Spatial-Wise Dynamic Gating Architecture for Convolutional Neural Networks
Autor: Sangmin Hyun, Chang Ho Ryu, Ju Yeon Kang, Hyun Jo Lim, Tae Hee Han
Publikováno v: Electronics; Volume 11; Issue 17; Pages: 2678
The explosive computation and memory requirements of convolutional neural networks (CNNs) hinder their deployment in resource-constrained devices. Because conventional CNNs perform identical parallelized computations even on redundant pixels, the sal
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68936814d7ed39f45ad1cb91ee071e27
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje