DAI SHIMIZU's Avatar

DAI SHIMIZU

@daishimizu.bsky.social

Brain Researcher@Osaka (Prev. Titech) M1 from 04/2025

5 Followers  |  11 Following  |  6 Posts  |  Joined: 23.11.2024  |  1.2984

Latest posts by daishimizu.bsky.social on Bluesky

Preview
ECA-ATCNet: Efficient EEG Decoding with Spike Integrated Transformer Conversion for BCI Applications The Brain–Computer Interface (BCI) has applications in smart homes and healthcare by converting EEG signals into control commands. However, traditional EEG signal decoding methods are affected by indi...

EEGNet for time series and CEBRA for classifications.
Mamba still requires more data.

www.mdpi.com/2076-3417/15...

09.03.2025 13:19 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
DREDge: robust motion correction for high-density extracellular recordings across species Nature Methods - DREDge is a software tool for motion correction of high-density electrophysiology recordings. It can handle action potential or local field potential data and is demonstrated on a...

Eddie Chang Lab is super.

www.nature.com/articles/s41...

08.03.2025 13:58 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

There is similar representation among language, artificial and biological neutral network.

www.biorxiv.org/content/10.1...

07.03.2025 13:18 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
MARBLE: interpretable representations of neural population dynamics using geometric deep learning - Nature Methods MARBLE uses geometric deep learning to map dynamics such as neural activity into a latent representation, which can then be used to decode the neural activity or compare it across systems.

Hmmm.
Interesting, looks like SEBRA before.

www.nature.com/articles/s41...

06.03.2025 13:32 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
From Language to Cognition: How LLMs Outgrow the Human Language Network Large language models (LLMs) exhibit remarkable similarity to neural activity in the human language network. However, the key properties of language shaping brain-like representations, and their evolu...

At the initial training stage, LLMs and the human brain's language areas show similarities; however, these similarities diminish as training progresses.

arxiv.org/abs/2503.01830

05.03.2025 19:38 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Predicted action-effects shape action representation through pre-activation of alpha oscillations - Communications Biology Combined evidence from behaviour, electrophysiology, and cognitive modelling supports a pre-activation of relevant action-effect codes when performing a voluntary action.

Prediction of action (shift of attention) is coded by Alpha.

www.nature.com/articles/s42...

04.03.2025 11:57 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

@daishimizu is following 11 prominent accounts