NIAI Lab @ Hanyang
Neuro-inspired AI group
Our group is interested in understanding principles that underlie learning and inference in the brain and machines, mainly by using tools from machine learning and statistics.
Publications
Osteoporosis prediction from hand and wrist x-rays using image segmentation and self-supervised learning
Lee, H., Hwang, U., Yu, S., Lee, C., Yoon, K.
Machine Learning for Health (ML4H) (2023) [pdf]
Hierarchical joint graph learning and multivariate time series forecasting
Kim, J., Lee, H., Yu, S., Hwang, U., Jung, W., Park, M., Yoon, K.
NeurIPS Workshop on Temporal Graph Learning (2023) [pdf]
Towards better generalization with flexible representation of multi-module graph neural networks
Lee, H., Yoon, K.
Transactions on Machine Learning Research (TMLR) (2023) [pdf]
Two-argument activation functions learn soft XOR operations like cortical neurons
Kim, J., Orhan, E., Yoon, K.*, Pitkow, X.*
IEEE Access (2022) [pdf]
생명체의 유연한 자연지능 모사방법과 데이터기반 방법을 융합한 통합 인공지능
Kim, J. et al.
한국정보과학회 (2021) [pdf]
Reviving and improving recurrent backpropagation
Liao, R., Xiong, Y., Fetaya, E., Zhang, L., Yoon, K., Pitkow, X., Urtasun, R., Zemel, R.
ICML (2018) [pdf]
A map-like micro-organization of grid cells in the medial entorhinal cortex
Gu, Y., Lewallen, S., Kinkhabwala, A. A., Domnisoru, C., Yoon, K., Gauthier, J., Fiete, I. R., Tank, D. W.
Cell (2018) [pdf]
Conference/Workshop
- Park, T., Yoon, K. “Connectivity inference of biological neural networks through systematic perturbations”, Korea Computer Congress, Jeju, South Korea (2022)
- Kim, J., Yoon, K. “Time-series forecasting with graph structure learning”, Korea Computer Congress, Jeju, South Korea (2022)
- Kang, D., Yoon, K. “Cortical surface segmentation based on graph neural networks using non- spherical spatial coordinates”, Korea Computer Congress, Jeju, South Korea (2022)
- Yoon, K., Orhan, E., Kim, J., Pitkow X. “Two-argument activation functions learn soft XOR operations like cortical neurons”, CRS21–Dialogues on Neural and Machine Intelligence, Lisbon, Portugal (2021) [poster]
- Park, H., Yoon, K. “Degree matters: assessing the generalization of graph neural network”, IEEE IC-NIDC, Beijing, China (2021)
- Yoon, K., Pitkow, X. “Learning nonlinearities for identifying regular structure in the brain’s inference algorithm.”, Computational and Systems Neuroscience, Denver, CO (2018)
- Yoon, K., Fiete, I. R. “Statistical framework for encoding and decoding grid cell population activity.”, Society for Neuroscience, Washington DC (2014)
- Yoon, K.∗, Lewallen, S.∗, Kinkhabwala, A. A., Tank, D. W., Fiete, I. R. “Grid cell responses in 1-d environments are consistent with 2-d continuous attractor dynamics.”, Society for Neuroscience, San Diego, CA (2013)
- Lewallen, S.∗, Yoon, K.∗, Kinkhabwala, A. A., Domnisoru, C., Tank, D. W., Fiete, I. R. “Grid cell responses in 1-d environments are linear slices of the 2-d periodic pattern.”, Society for Neuroscience, San Diego, CA (2013)
- Yoon, K., Kinkhabwala, A. A., Tank, D. W., Fiete, I. R. “Are aperiodic 1D grid cell responses consistent with low-dimensional continuous attractor dynamics?”, Computational and Systems Neu- roscience, Salt Lake City, UT (2013)
- Yoon, K., Barry, C., Buice, M. A., Burgess, N. Fiete, I. R. “Are grid-cell responses very low- dimensional?”, Computational and Systems Neuroscience, Salt Lake City, UT (2012)
- Yoon, K., Barry, C., Burgess, N., Fiete, I. R. “Assessing the role of feedback in spatially pat- terened grid cell responses.” Society for Neuroscience, San Diego, CA (2010) *Equal contributions.