J
Jinwook Oh
Researcher at IBM
Publications - 48
Citations - 924
Jinwook Oh is an academic researcher from IBM. The author has contributed to research in topics: Cognitive neuroscience of visual object recognition & Network on a chip. The author has an hindex of 14, co-authored 46 publications receiving 697 citations. Previous affiliations of Jinwook Oh include KAIST.
Papers
More filters
Proceedings ArticleDOI
A 86mW 98GOPS ANN-searching processor for Full-HD 30fps video object recognition with zeroless locality-sensitive hashing
TL;DR: To reduce the external bandwidth required in nearest neighbor searching, this chip utilizes an on-chip cache for transaction reduction and the zeroless locality-sensitive hashing (zeroless-LSH) operation for required data suppression.
Proceedings ArticleDOI
Online Reinforcement Learning NoC for portable HD object recognition processor
TL;DR: Heterogeneous multi-core object recognition processor with Reinforcement Learning (RL) NoC is proposed for efficient portable HD object recognition and the overall execution time of the object recognition is reduced by 38%.
Proceedings ArticleDOI
An area efficient shared synapse cellular neural network for low power image processing
TL;DR: An area and power efficient cellular neural network (CNN) that enables real-time image processing by halves the number of required synapse multipliers and reduces power and area by 46% and 41%, respectively.
Proceedings ArticleDOI
1.15mW mixed-mode neuro-fuzzy accelerator for keypoint localization in image processing
TL;DR: A mixed-mode neuro-fuzzy accelerator is proposed for keypoint localization of image features of Scale Invariant Feature Transform (SIFT) algorithm and it achieves 43% processing time reduction and also results in 19.4% time reduction of image feature extraction process.
Proceedings ArticleDOI
An asynchronous mixed-mode neuro-fuzzy controller for energy efficient machine intelligence SoC
TL;DR: A neuro-fuzzy controller with a delay prediction unit and a new ISA is introduced to modify the stage depth of mixed-mode pipeline incorporating with highly parallel special function units to enable energy efficient implementation of machine intelligence SoC.