no code implementations • 6 Oct 2022 • Takuma Sumi, Hideaki Yamamoto, Yuichi Katori, Satoshi Moriya, Tomohiro Konno, Shigeo Sato, Ayumi Hirano-Iwata
We first show that modular BNNs can be used to classify static input patterns with a linear decoder and that the modularity of the BNNs positively correlates with the classification accuracy.
no code implementations • 20 Jun 2020 • Keita Tokuda, Naoya Fujiwara, Akihito Sudo, Yuichi Katori
Here, we propose that the massive gap junctions between the Golgi cells contribute to the representational complexity of the granular layer of the cerebellum by inducing chaotic dynamics.