Connectionists: New paper about supervised learning in spiking neural networks

[Filip Ponulak]

Dear Colleagues,
I would like to draw your attention to the following paper:
'Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence
Learning, Classification, and Spike Shifting', Neural Computation,
Vol. 22, No. 2, Pages 467-510, 2010 (doi:10.1162/neco.2009.11-08-901)

by Filip Ponulak and Andrzej Kasinski

The paper can be viewed and downloaded from the following location:
http://www.mitpressjournals.org/doi/pdf/10.1162/neco.2009.11-08-901

Abstract:
---------
Learning from instructions or demonstrations is a fundamental property
of our brain necessary to acquire new knowledge and develop novel
skills or behavioral patterns. This type of learning is thought to be
involved in most of our daily routines. Although the concept of
instruction-based learning has been studied for several decades, the
exact neural mechanisms implementing this process remain unrevealed.
One of the central questions in this regard is, How do neurons learn
to reproduce template signals (instructions) encoded in precisely
timed sequences of spikes?

Here we present a model of supervised learning for biologically
plausible neurons that addresses this question. In a set of
experiments, we demonstrate that our approach enables us to train
spiking neurons to reproduce arbitrary template spike patterns in
response to given synaptic stimuli even in the presence of various
sources of noise.

We show that the learning rule can also be used for decision-making
tasks. Neurons can be trained to classify categories of input signals
based on only a temporal configuration of spikes. The decision is
communicated by emitting precisely timed spike trains associated with
given input categories. Trained neurons can perform the classification
task correctly even if stimuli and corresponding decision times are
temporally separated and the relevant information is consequently
highly overlapped by the ongoing neural activity.

Finally, we demonstrate that neurons can be trained to reproduce
sequences of spikes with a controllable time shift with respect to
target templates. A reproduced signal can follow or even precede the
targets. This surprising result points out that spiking neurons can
potentially be applied to forecast the behavior (firing times) of
other reference neurons or networks.

-------

All comments and ideas regarding the results presented in the paper
will be highly appreciated.

Best regards,
Filip Ponulak

(Apologies for crossposting)


---------------------------------------------------------------------------------
Neuroscience Institute & Dept. of Molecular Biology,
Princeton University, Princeton  NJ  08544, USA
---
Institute of Control and Information Engineering,
Poznan University of Technology, 60965 Poznan, Poland
---
Phone: +1-609-258-7316
Email: fponulak at princeton.edu
---------------------------------------------------------------------------------