A computational passage-of-time model of the cerebellar Purkinje cell in eyeblink conditioning

Autor: Matthew Ricci, Junkyung Kim, Fredrik Johansson

Publikováno v: Frontiers in Computational Neuroscience, Vol 17 (2023)

The cerebellar Purkinje cell controlling eyeblinks can learn, remember, and reproduce the interstimulus interval in a classical conditioning paradigm. Given temporally separated inputs, the cerebellar Purkinje cell learns to pause its tonic inhibitio

Externí odkaz: https://doaj.org/article/1673ad98a8e946a1abe5712d6b8c9bdc

Differential involvement of EEG oscillatory components in sameness vs. spatial-relation visual reasoning tasks

Autor: Junkyung Kim, Canhuang Luo, Thomas Serre, Andrea Alamia, Matthew Ricci, Rufin VanRullen

Publikováno v: eNeuro
eNeuro, Society for Neuroscience, 2021, 8 (1), pp.ENEURO.0267-20.2020. ⟨10.1523/ENEURO.0267-20.2020⟩
eNeuro, 2021, 8 (1), pp.ENEURO.0267-20.2020. ⟨10.1523/ENEURO.0267-20.2020⟩

The development of deep convolutional networks (DCNs) has recently led to great successes in computer vision and have become de facto computational models of vision. However, a growing body of work suggests that they exhibit critical limitations beyo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::906a70371095e6e7a05a19e97c809df4
https://hal.archives-ouvertes.fr/hal-03092841/document

Disentangling neural mechanisms for perceptual grouping

Autor: Kalpit Thakkar, Drew Linsley, Thomas Serre, Junkyung Kim

Publikováno v: International Conference on Learning Representations
International Conference on Learning Representations, 2020, Addis Abbeba (virtual), Ethiopia

Forming perceptual groups and individuating objects in visual scenes is an essential step towards visual intelligence. This ability is thought to arise in the brain from computations implemented by bottom-up, horizontal, and top-down connections betw

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5dd1a14f4b8e2fe748d2f4f6ba30a6a8
http://arxiv.org/abs/1906.01558

Optimizing a recurrent neural architecture for contour detection produces a tilt illusion

Autor: Thomas Serre, Drew Linsley, Junkyung Kim

Publikováno v: 2019 Conference on Cognitive Computational Neuroscience.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2ce86638cbd4e6b070f29c537abb1215
https://doi.org/10.32470/ccn.2019.1244-0

Highly pipelined Accelerator for Convolutional Neural Network

Autor: Jong-Wha Chong, Junkyung Kim, HwangSik Bae, Kyeong Yuk Min

Publikováno v: ICCE

We propose a highly pipelined accelerator (HIPA) for the convolutional neural network (CNN). The CNN achieves remarkable performance in computer vision application with high computational power and low energy efficiency than conventional algorithms.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7d69a6834a1a4869d69dcb341ac0c09e
https://doi.org/10.1109/icce.2019.8662040