"New Ideas in Theoretical Neuroscience” seminar (GNT)

May 4th, 2017 at 14:00h in Salle Langevin, 29 rue d’ulm

"Spiking neurons can discover predictive features by aggregate-label learning"


The brain routinely discovers sensory clues that predict opportunities or dangers. However, it is unclear how neural learning processes can bridge the typically long delays between sensory clues and behavioral outcomes. Here, I introduce a learning concept, aggregate-label learning, that enables biologically plausible model neurons to solve this temporal credit assignment problem. Aggregate-label learning matches a neuron’s number of output spikes to a feedback signal that is proportional to the number of clues but carries no information about their timing. Aggregate-label learning outperforms stochastic reinforcement learning at identifying predictive clues and is able to solve unsegmented speech-recognition tasks. Furthermore, it allows unsupervised neural networks to discover reoccurring constellations of sensory features even when they are widely dispersed across space and time.

Biography: Robert Gütig is currently an independent group leader at the Max Planck Institute of Experimental Medicine in Goettingen (Germany). His research concentrates on spike-based learning and information processing in neural networks. Robert Gütig was trained in Physics at the Free University of Berlin (Germany) and the University of Cambridge (UK). He did his PhD in Computational Neuroscience with Ad Aertsen at University of Freiburg (Germany) and worked as a postdoc with Haim Sompolinsky at the Hebrew University of Jerusalem (Israel).