[Comp-neuro] Paper: Recognition by Variance: Learning Rules for Spatiotemporal Patterns

[Omri Barak]

The following new paper was accepted for publication in Neural Computation,
and is currently available at

 

http://www.weizmann.ac.il/home/bnmisha/publications/papers/omriNN06.pdf

 

We welcome your comments.

 

TITLE:

Recognition by Variance: Learning Rules for Spatiotemporal Patterns

 

AUTHORS:

Omri Barak and Misha Tsodyks

 

ABSTRACT:

Recognizing specific spatiotemporal patterns of activity, which take place
at timescales much larger than the synaptic transmission and membrane time
constants, is a demand from the nervous system exemplified, for instance, by
auditory processing. We consider the total synaptic input that a single
read-out neuron receives upon presentation of spatiotemporal spiking input
patterns. Relying on the monotonic relation between the mean and the
variance of a neuron's input current and its spiking output, we derive
learning rules that increase the variance of the input current evoked by
learned patterns relative to that obtained from random background patterns.
We demonstrate that the model can successfully recognize a large number of
patterns, and exhibits a slow deterioration in performance with increasing
number of learned patterns. In addition, robustness to time warping of the
input patterns is revealed to be an emergent property of the model. Using a
leaky Integrate and Fire realization of the read-out neuron, we demonstrate
that the above results also apply when considering spiking output.

 

Best,

Omri Barak

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.neuroinf.org/pipermail/comp-neuro/attachments/20060302/601f1ad1/attachment.html