Package topo :: Package outputfns :: Module basic :: Class ActivityAveragingOF

Class ActivityAveragingOF

                                  object --+            
                                           |            
base.parameterizedobject.ParameterizedObject --+        
                                               |        
                  base.functionfamilies.OutputFn --+    
                                                   |    
                                   OutputFnWithState --+
                                                       |
                                                      ActivityAveragingOF

Calculates the average of the input activity.

The average is calculated as an exponential moving average, where the weighting for each older data point decreases exponentially. The degree of weighing for the previous values is expressed as a constant smoothing factor.

The plastic parameter allows the updating of the average values to be disabled temporarily, e.g. while presenting test patterns.

Nested Classes

[hide private]

Inherited from base.parameterizedobject.ParameterizedObject: __metaclass__

Instance Methods

[hide private]

__init__(self, **params)

source code

__call__(self, x)

source code

Inherited from OutputFnWithState: override_plasticity_state, restore_plasticity_state

Inherited from base.functionfamilies.OutputFn: __add__

Inherited from base.parameterizedobject.ParameterizedObject: __getstate__, __repr__, __setstate__, __str__, as_uninitialized, debug, defaults, force_new_dynamic_value, get_param_values, get_value_generator, inspect_value, message, print_param_values, script_repr, verbose, warning

Inherited from base.parameterizedobject.ParameterizedObject (private): _check_params, _instantiate_param, _set_name, _setup_params

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

Class Methods

[hide private]

Inherited from base.parameterizedobject.ParameterizedObject: params, print_param_defaults

Class Variables

[hide private]

step = Number(default= 1, doc= ...
How often to update the average.

smoothing = <topo.base.parameterclasses.Number object at 0x9db...
The degree of weighting for the previous average, when calculating the new average.

initial_average = <topo.base.parameterclasses.Number object at...
Starting value for the average activity.

Inherited from OutputFnWithState: plastic

Inherited from base.functionfamilies.OutputFn: norm_value

Inherited from base.parameterizedobject.ParameterizedObject: name, print_level

Properties

[hide private]

Inherited from object: __class__

Method Details

[hide private]

init(self, **params)
(Constructor)

source code

Overrides: OutputFnWithState.__init__

call(self, x)
(Call operator)

source code

Overrides: base.functionfamilies.OutputFn.__call__

Class Variable Details

[hide private]

step

How often to update the average.

For instance, step=1 means to update it every time this OF is called; step=2 means to update it every other time.

Value:

Number(default= 1, doc= """
        How often to update the average.

        For instance, step=1 means to update it every time this OF is
        called; step=2 means to update it every other time.""")

smoothing

The degree of weighting for the previous average, when calculating the new average.

Value:

Number(default= 0.9997, doc= """
        The degree of weighting for the previous average, when calculating the new
 average.""")

initial_average

Starting value for the average activity.

Value:

Number(default= 0, doc= "Starting value for the average activity.")

Class ActivityAveragingOF

__init__(self, **params) (Constructor)

__call__(self, x) (Call operator)

step

smoothing

initial_average

init(self, **params)
(Constructor)

call(self, x)
(Call operator)