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.
Robert Guetig 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 Guetig 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).