Timezone: »
We consider a statistical framework in which recurrent networks of spiking neurons learn to generate spatio-temporal spike patterns. Given biologically realistic stochastic neuronal dynamics we derive a tractable learning rule for the synaptic weights towards hidden and visible neurons that leads to optimal recall of the training sequences. We show that learning synaptic weights towards hidden neurons significantly improves the storing capacity of the network. Furthermore, we derive an approximate online learning rule and show that our learning rule is consistent with Spike-Timing Dependent Plasticity in that if a presynaptic spike shortly precedes a postynaptic spike, potentiation is induced and otherwise depression is elicited.
Author Information
Johanni Brea (Universität Bern)
Walter Senn (University of Bern)
Jean-Pascal Pfister (Cambridge University)
Related Events (a corresponding poster, oral, or spotlight)
-
2011 Spotlight: Sequence learning with hidden units in spiking neural networks »
Tue. Dec 13th 11:44 -- 11:48 AM Room
More from the Same Authors
-
2018 Poster: Dendritic cortical microcircuits approximate the backpropagation algorithm »
João Sacramento · Rui Ponte Costa · Yoshua Bengio · Walter Senn -
2018 Oral: Dendritic cortical microcircuits approximate the backpropagation algorithm »
João Sacramento · Rui Ponte Costa · Yoshua Bengio · Walter Senn -
2009 Workshop: Normative electrophysiology: Explaining cellular properties of neurons from first principles »
Jean-Pascal Pfister · Mate Lengyel -
2009 Poster: Know Thy Neighbour: A Normative Theory of Synaptic Depression »
Jean-Pascal Pfister · Peter Dayan · Mate Lengyel -
2009 Oral: Know Thy Neighbour: A Normative Theory of Synaptic Depression »
Jean-Pascal Pfister · Peter Dayan · Mate Lengyel