Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
A systematic comparison between visual cues for boundary detection
Learning long-range spatial dependencies with horizontal gated-recurrent units
This work introduces the horizontal gated-recurrent unit (hGRU) to learn intrinsic horizontal connections -- both within and across feature columns, and demonstrates that a single hGRU layer matches or outperforms all tested feedforward hierarchical baselines including state-of-the-art architectures which have orders of magnitude more free parameters.
Not-So-CLEVR: Visual Relations Strain Feedforward Neural Networks
Motivated by the comparable success of biological vision, it is argued that feedback mechanisms including working memory and attention are the key computational components underlying abstract visual reasoning.
Not-So-CLEVR: learning same–different relations strains feedforward neural networks
It is shown that feedforward neural networks struggle to learn abstract visual relations that are effortlessly recognized by non-human primates, birds, rodents and even insects, and that feedback mechanisms such as attention, working memory and perceptual grouping may be the key components underlying human-level abstract visual reasoning.
Epileptic seizure detection for multi-channel EEG with deep convolutional neural network
- Chulkyun Park, Gwangho Choi, Jongwha Chong
- Computer ScienceInternational Conference on Electronics…
- 2 April 2018
The proposed network is designed for multi-channel EEG signals and considers spatio-temporal correlation, a feature in epileptic seizure detection, using 1D and 2D convolutional layers, and achieves 90.5% prediction accuracy with SNUH-HYU EEG dataset.
Disentangling neural mechanisms for perceptual grouping
This work systematically evaluates neural network architectures featuring combinations of bottom-up, horizontal and top-down connectivity on two synthetic visual tasks, which stress low-level `gestalt' vs. high-level object cues for perceptual grouping and demonstrates how a model featuring all of these interactions can more flexibly learn to form perceptual groups.
A Novel Multi-scale 3D CNN with Deep Neural Network for Epileptic Seizure Detection
- Gwangho Choi, Chulkyun Park, J. Chong
- Computer ScienceIEEE International Conference on Consumer…
- 6 March 2019
A Multi-scale 3D-CNN with Deep Neural Network (DNN) model for non-patient-specific seizure detection that achieves the sensitivity of 89.4% and 97% and a false positive rate of 0.5/hours on the CHB-MIT database, and the SNUH database, respectively.
Same-different problems strain convolutional neural networks
It is argued that feedback mechanisms including attention and perceptual grouping may be the key computational components underlying abstract visual reasoning in modern machine vision algorithms.
Recurrent neural circuits for contour detection
This study suggests that the orientation-tilt illusion is a byproduct of neural circuits that help biological visual systems achieve robust and efficient contour detection, and that incorporating these circuits in artificial neural networks can improve computer vision.
Sample-efficient image segmentation through recurrence
It is demonstrated that γ-Net performs on par or better than state-of-the-art architectures for dense prediction in both natural image and cell segmentation datasets and that similar principles can improve the data efficiency of computer vision systems.