Kuan Han

This paper uses a variational autoencoder to disentangle sources of variation in resting state fMRI data and shows that latent representations can reliably identify subjects from a large group.

This study maps cortical representations of semantic relations using fMRI data, showing that semantic categories and relations are encoded in overlapping patterns across brain networks.

This paper uses a variational autoencoder to model and decode fMRI activity in the visual cortex, finding lower prediction accuracy compared to CNNs but successful decoding of latent variables.

This paper introduces a deep recurrent neural network to model process memory in visual processing and shows it better predicts cortical responses to natural movies than a standard CNN.