1 code implementation • 2 Jun 2022 • Reinmar J Kobler, Jun-Ichiro Hirayama, Qibin Zhao, Motoaki Kawanabe
To achieve this, we propose a new building block for geometric deep learning, which we denote SPD domain-specific momentum batch normalization (SPDDSMBN).
1 code implementation • 30 Jul 2021 • Reinmar J. Kobler, Jun-Ichiro Hirayama, Lea Hehenberger Catarina Lopes-Dias, Gernot R. Müller-Putz, Motoaki Kawanabe
Riemannian tangent space methods offer state-of-the-art performance in magnetoencephalography (MEG) and electroencephalography (EEG) based applications such as brain-computer interfaces and biomarker development.
no code implementations • 5 Jun 2021 • Yu Takagi, Laurence T. Hunt, Ryu Ohata, Hiroshi Imamizu, Jun-Ichiro Hirayama
In this paper, we develop a new method for cross-areal interaction analysis that uses the rich task or stimulus parameters to reveal how and what types of information are shared by different neural populations.
1 code implementation • NeurIPS 2020 • Yu Takagi, Steven W. Kennerley, Jun-Ichiro Hirayama, Laurence T. Hunt
This yields interpretable components that express which variables are shared between different brain regions and when this information is shared across time.
Neurons and Cognition
no code implementations • ICML 2017 • Jun-Ichiro Hirayama, Aapo Hyvärinen, Motoaki Kawanabe
We present a novel probabilistic framework for a hierarchical extension of independent component analysis (ICA), with a particular motivation in neuroscientific data analysis and modeling.
no code implementations • 14 Feb 2012 • Michael Gutmann, Jun-Ichiro Hirayama
We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively.
no code implementations • NeurIPS 2011 • Jun-Ichiro Hirayama, Aapo Hyvärinen
Here, we propose a principled probabilistic model to model the energy- correlations between the latent variables.