Peiyu Chen

This study shows that efficient neural representations in working memory can lead to errors, and cholinergic stimulation improves performance by using more distinct representations.

This paper introduces BrainRNN, a brain-like recurrent neural network architecture, and shows that structural constraints lead to functional organization similar to the human cortex.

The paper uses graph neural networks to predict functional connectivity from structural connectivity in human brain networks, finding strong group-common structure-function coupling with some individual-specific effects.