Package topo :: Package learningfn

Package learningfn

A family of function objects for changing a set of weights over time.

Learning functions come in two varieties: LearningFunction, and CFPLearningFunction. A LearningFunction (e.g. Hebbian) applies to one set of weights, typically from one ConnectionField. To apply learning to an entire CFProjection, a LearningFunction can be plugged in to CFPLF_Plugin. CFPLF_Plugin is one example of a CFPLearningFunction, which is a function that works with the entire Projection at once. Some optimizations and algorithms can only be applied at the full CFPLearningFn level, so there are other CFPLearningFns beyond CFPLF_Plugin.

Any new learning functions added to this directory will automatically become available for any model.

$Id: __init__.py 8936 2008-08-21 13:23:31Z ceball $

Version: $Revision: 8936 $

Submodules

[hide private]

topo.learningfn.basic: Basic learning functions.
topo.learningfn.optimized: Learning functions (see basic.py) and projection-level learning functions (see projfn.py) written in C to optimize performance.
topo.learningfn.projfn: Learning functions for Projections.
topo.learningfn.som: SOM-based learning functions for CFProjections.

Classes

[hide private]

BCMFixed
Bienenstock, Cooper, and Munro (1982) learning rule with a fixed threshold.

CPCA
CPCA (Conditional Principal Component Analysis) rule.

Covariance
Covariance learning rule supporting either input or unit thresholds.

Hebbian
Basic Hebbian rule; Dayan and Abbott, 2001, equation 8.3.

IdentityLF
Identity function; does not modify the weights.

LearningFn
Abstract base class for learning functions that plug into CFPLF_Plugin.

Oja
Oja's rule (Oja, 1982; Dayan and Abbott, 2001, equation 8.16.)

Variables

[hide private]

__package__ = 'topo.learningfn'