Understanding human cognition and neural systems has been an area of active research for the past several decades, however there is still a lot that remains to be understood. Knowledge about these systems is a key component to design systems which can experience and understand the world in the way humans do in order to truly become “intelligent”. The problem however is an extremely challenging one due to the extremely noisy nature of signals of neural activity like EEG, fMRI etc.
In this research area we attempt to decode and reconstruct the Neural Basis of Real World Social Perception by trying to find relations between intra-cranial EEG signals and human expressions, pose, actions, emotions etc. This will allow us to decode the spatiotemporal patterns of neural activity and reconstruct the expressive features of people which they see at these different levels on a moment-to-moment basis. This project involves combining state of the art Computer Vision and Statistical Machine Learning techniques with the understanding of the human cognitive systems to obtain insights about the working of the human brain.