Package crino :: Module module :: Class Activation
[hide private]
[frames] | no frames]

Class Activation

source code

Known Subclasses:

An Activation module computes its outputs without any parameter, but with a function f : ℝn −  > ℝn applied to its inputs vector. This function is generally non-linear, because its purpose is to provide non-linearity to the neural network.
Instance Methods [hide private]
 
__init__(self, nOutputs, nInputs=None)
Constructs a new Activation module.
source code
 
prepareParams(self)
Do nothing, as an activation module doesn't have params.
source code

Inherited from Standalone: prepareGeometry

Inherited from Module: criterionFunction, forward, forwardFunction, holdFunction, linkInputs, linkModule, prepare, prepareBackup, prepareOutput, restoreFunction, save, trainFunction

Instance Variables [hide private]

Inherited from Module: backupParams, inputs, nInputs, nOutputs, outputs, params, prepared

Method Details [hide private]

__init__(self, nOutputs, nInputs=None)
(Constructor)

source code 
Constructs a new Activation module.
Parameters:
  • nOutputs (int) - The outputs size.
  • nInputs (int) - The inputs size.
Overrides: Module.__init__

prepareParams(self)

source code 
Do nothing, as an activation module doesn't have params.
Overrides: Module.prepareParams