Helmholtz Lecture by Ruffin VanRullen

Rufin VanRullen is AI Research Chair at the Centre for Brain and Cognition Research and the Artificial and Natural Intelligence Institute in Toulouse, France. His work investigates the neural dynamics of visual perception, attention and consciousness, with a focus on neural oscillations, neural coding and deep learning.
Abstract: In recent years, artificial neural networks have demonstrated human-like or super-human performance in many tasks including image or speech recognition, natural language processing (NLP), playing Go, chess, poker and video-games. One remarkable feature of the resulting models is that they can develop very intuitive latent representations of their inputs. In these latent spaces, simple linear operations tend to give meaningful results, as in the well-known analogy QUEEN-WOMAN+MAN=KING. We postulate that human brain representations share essential properties with these deep learning latent spaces. To verify this, we test whether artificial latent spaces can serve as a good model for decoding brain activity. We report improvements over state-of-the-art performance for reconstructing seen and imagined face images from fMRI brain activation patterns, using the latent space of a GAN (Generative Adversarial Network) model coupled with a Variational AutoEncoder (VAE). With another GAN model (BigBiGAN), we can decode and reconstruct natural scenes of any category from the corresponding brain activity. Our results suggest that deep learning can produce high-level representations approaching those found in the human brain. Finally, I will discuss whether these deep learning latent spaces could be relevant to the study of consciousness.
We will continue hosting these meetings on Zoom. One benefit of this is that we can have guests in our audience from all around the world, so please feel free to also forward this invite to interested colleagues elsewhere. It is no longer necessary for external guests to notify the hosts of their attendance.