[Comp-neuro] role of noise in learning
maass at igi.tugraz.at
Thu Jul 24 14:01:33 CEST 2008
I would like to add to your discussion that "noise" is obviously
needed for reward-based learning in networks of neurons:
If such networks have to learn without a supervisor (which tells the
neurons during training when they should fire), they have to explore
different ways of responding to a stimulus, until the come across
responses that are "rewarded" because they provide good system
performance. This exploration would appear as "noise" in most analyses.
In fact, one might conjecture that networks of neurons are genetically
endowed with the capability to go through rather clever exploration
patterns (i.e, particular types of "noise"), in order to enable fast
convergence of such reinforcement learning schemes.
The role of noise in reward-based learning has been analyzed by a number
of people, see #183 on
for a very recent contribution (and references to earlier work).
Prof. Dr. Wolfgang Maass
Institut fuer Grundlagen der Informationsverarbeitung
Technische Universitaet Graz
Inffeldgasse 16b , A-8010 Graz, Austria
More information about the Comp-neuro