Package topo :: Package learningfn :: Module projfn
[hide private]
[frames] | no frames]

Module projfn

source code

Learning functions for Projections.

For example, CFProjectionLearningFunctions compute a new set of ConnectionFields when given an input and output pattern and a set of ConnectionField objects.

$Id: projfn.py 11316 2010-07-27 17:52:53Z ceball $


Version: $Revision: 11316 $

Classes [hide private]
  CFPLF_EuclideanHebbian
Hebbian CFProjection learning rule based on Euclidean distance.
  CFPLF_Trace
LearningFn that incorporates a trace of recent activity, not just the current activity.
  CFPLF_OutstarHebbian
CFPLearningFunction applying the specified (default is Hebbian) single_cf_fn to each CF, where normalization is done in an outstar-manner.
  HomeoSynaptic
Learning function using homeostatic synaptic scaling from Sullivan & de Sa, "Homeostatic Synaptic Scaling in Self-Organizing Maps", Neural Networks (2006), 19(6-7):734-43.
  CFPLF_PluginScaled
CFPLearningFunction applying the specified single_cf_fn to each CF.
Variables [hide private]
  __package__ = 'topo.learningfn'