Package topo :: Package learningfn :: Module basic :: Class CPCA
[hide private]
[frames] | no frames]

Class CPCA

source code


CPCA (Conditional Principal Component Analysis) rule.

(See O'Reilly and Munakata, Computational Explorations in Cognitive Neuroscience, 2000, equation 4.12.)

Increases each weight in proportion to the product of this neuron's activity, input activity, and connection weights.

Has built-in normalization, and so does not require output_fn normalization for stability. Intended to be a more biologically plausible version of the Oja rule.

Submitted by Veldri Kurniawan and Lewis Ng.

Nested Classes [hide private]

Inherited from param.parameterized.Parameterized: __metaclass__

Instance Methods [hide private]
 
__call__(self, input_activity, unit_activity, weights, single_connection_learning_rate)
Update the value of the given weights matrix based on the input_activity matrix (of the same size as the weights matrix), the response of this unit (the unit_activity), and the previous weights matrix governed by a per-connection learning rate.
source code

Inherited from param.parameterized.Parameterized: __getstate__, __init__, __repr__, __setstate__, __str__, debug, defaults, force_new_dynamic_value, get_param_values, get_value_generator, inspect_value, message, print_param_values, script_repr, set_default, set_dynamic_time_fn, set_param, state_pop, state_push, verbose, warning

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __setattr__, __sizeof__, __subclasshook__

Class Methods [hide private]

Inherited from param.parameterized.Parameterized: params, print_param_defaults

Class Variables [hide private]
  name = <param.parameterized.String object at 0xb287c6c>
String identifier for this object.

Inherited from param.parameterized.Parameterized: print_level

Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__call__(self, input_activity, unit_activity, weights, single_connection_learning_rate)
(Call operator)

source code 
Update the value of the given weights matrix based on the input_activity matrix (of the same size as the weights matrix), the response of this unit (the unit_activity), and the previous weights matrix governed by a per-connection learning rate.
Overrides: base.functionfamily.LearningFn.__call__