You are here: Home Bernstein Seminar 2016 Robert Gütig (Max Planck Institute …

Banner Bernstein Seminar

Robert Gütig (Max Planck Institute for Experimental Medicine, Dept. of Theoretical Neuroscience) | Spiking neurons can discover predictive features by aggregate-label learning

When Dec 13, 2016
from 05:15 PM to 06:45 PM
Where BCF Lecture Hall, Hansastr. 9a
Contact Name Ad Aersten
Add event to calendar vCal
iCal

 

Abstract

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.

 

 

Supported by

Bernstein Center Freiburg | PhD Program BrainDiscDeutscher Akademischer Austauschdienst DAADFederal Ministery of Education and ResearchCarl Zeiss FoundationNeurexNeuroCampusEU Development FundEU InterregNeurAGBrainLinks BrainTools

 

All upcoming scientific events

Back to overview

All Bernstein Seminars

2021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 | 2011 | 2010

Filed under: