אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

Reconstructing observed images from fMRI brain recordings is challenging. Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i.e., images with their corresponding fMRI responses) to span the huge space of natural images is prohibitive for many reasons. We present a novel approach which, in addition to the scarce labeled data (training pairs), allows to train fMRI-to-image reconstruction networks also on "unlabeled" data (i.e., images without fMRI recording, and fMRI recording without images). The proposed model utilizes both an Encoder network (image-to-fMRI) and a Decoder network (fMRI-to-image). Concatenating these two networks back-to-back (Encoder-Decoder & Decoder-Encoder) allows augmenting the training with both types of unlabeled data. Importantly, it allows training on the unlabeled test-fMRI data. This self-supervision adapts the reconstruction network to the new input test-data, despite its deviation from the statistics of the scarce training data.

Short bio:
Guy is a PhD student from the Michal Irani Computer Vision Lab at WIS. His research established a new line of work in his group on reconstruction of presented visual stimuli from evoked brain activity using Deep Learning. Guy holds a BSc in Computer Engineering & Physics (Hebrew U.), MSc in Physics & Biology (WIS, advised by Prof. Uri Alon) and is now pursuing his PhD in CS & Neuroscience (WIS).