Deep image reconstruction from human brain activity

Shen, Horikawa, Majima, and Kamitani (2019) Deep image reconstruction from human brain activity. PLos Comput Biol. (bioRxiv preprint)<br>Here we provide DNN features decoded from human brain activity (decodedfeatures-*.mat files) as well as preprocessed fMRI data used for the decoding (sub-*.h5 files).<br><br>Raw fMRI data are available at OpenNeuro.<br><br>Demo code is available at GitHub.<br><b>History</b><br>2020-09-08: True DNN features (unit activations) of VGG19 for natural image training images were added.<br><br>2020-08-05: fMRI data version 2, which applied slightly different preprocessng and ROIs from the original study, were added (for the natural image experiment only; *_perceptionNaturalImageTraining/Test_VC_v2.h5).<br><br>2020-05-18: The following fMRI data files of artificial images, letters, and imagery experiments contained incorrect samples and were fixed.<br>- sub-01_perceptionLetterImage_original_VC.h5- sub-02_perceptionArtificialImage_original_VC.h5<br>- sub-02_perceptionLetterImage_original_VC.h5- sub-02_imagery_original_VC.h5<br>- sub-03_perceptionArtificialImage_original_VC.h5- sub-03_perceptionLetterImage_original_VC.h5- sub-03_imagery_original_VC.h5<br>