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

Class HomeoSynaptic

source code


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.

Does not necessarily require output_fn normalization for stability.

Nested Classes [hide private]

Inherited from param.parameterized.Parameterized: __metaclass__

Instance Methods [hide private]
 
__init__(self, **params)
x.__init__(...) initializes x; see x.__class__.__doc__ for signature
source code
 
__call__(self, iterator, input_activity, output_activity, learning_rate, **params)
Update the value of the given weights matrix based on the input_activity matrix (of the same size as the weights matrix) and the response of this unit (the unit_activity), governed by a per-connection learning rate.
source code

Inherited from base.cf.CFPLearningFn: constant_sum_connection_rate

Inherited from param.parameterized.Parameterized: __getstate__, __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]
  single_cf_fn = param.ClassSelector(LearningFn, default= Hebbia...
LearningFn that will be applied to each CF individually
  beta_n = param.Number(default= 0.01, bounds= (0, None), doc= "...
homeostatic learning rate
  beta_c = param.Number(default= 0.005, bounds= (0, None), doc= ...
time window over which the neuron's firing rate is averaged
  activity_target = param.Number(default= 0.1, bounds= (0, None)...
Target average activity
  name = <param.parameterized.String object at 0xb2872ac>
String identifier for this object.

Inherited from param.parameterized.Parameterized: print_level

Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__init__(self, **params)
(Constructor)

source code 
x.__init__(...) initializes x; see x.__class__.__doc__ for signature
Overrides: object.__init__
(inherited documentation)

__call__(self, iterator, input_activity, output_activity, learning_rate, **params)
(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) and the response of this unit (the unit_activity), governed by a per-connection learning rate.
Overrides: base.cf.CFPLearningFn.__call__

Class Variable Details [hide private]

single_cf_fn

LearningFn that will be applied to each CF individually
Value:
param.ClassSelector(LearningFn, default= Hebbian(), doc= "LearningFn that will be \
applied to each CF individually")

beta_n

homeostatic learning rate
Value:
param.Number(default= 0.01, bounds= (0, None), doc= "homeostatic learning rate")

beta_c

time window over which the neuron's firing rate is averaged
Value:
param.Number(default= 0.005, bounds= (0, None), doc= "time window over which the n\
euron's firing rate is averaged")

activity_target

Target average activity
Value:
param.Number(default= 0.1, bounds= (0, None), doc= "Target average activity")