Inheritance diagram for FakeSigmoidFunction:


Constructors | |
| FakeSigmoidFunction (Real l=1.0) | |
| FakeSigmoidFunction (PropertySettings &prop) | |
| virtual | ~FakeSigmoidFunction () |
Interface | |
| bool | setLambda (const Variant &v) |
| Variant | getLambda () |
| virtual void | apply (RealVec &inputs, RealVec &outputs) |
| virtual void | derivate (const RealVec &x, const RealVec &y, RealVec &d) const |
| virtual FakeSigmoidFunction * | clone () const |
Public Attributes | |
| Real | lambda |
| Properties | ||||
| Name | Type [isVector] | Access mode | Description | Class |
|---|---|---|---|---|
| typename | string | read-only | Class's type | Propertized |
| lambda | Real | read/write | function's slope | this |
| FakeSigmoidFunction | ( | Real | l = 1.0 |
) |
Construct a sigmoid updater with parameter l
| FakeSigmoidFunction | ( | PropertySettings & | prop | ) |
Construct
| virtual ~FakeSigmoidFunction | ( | ) | [inline, virtual] |
Destructor
| bool setLambda | ( | const Variant & | v | ) |
Set the slope of FakeSigmoidFunction
| Variant getLambda | ( | ) |
Return the slope of FakeSigmoidFunction
Implement the updating method
Reimplemented from OutputFunction.
return the approximation commonly used in backpropagation learning: x(1-x)
Reimplemented from DerivableOutputFunction.
| virtual FakeSigmoidFunction* clone | ( | ) | const [virtual] |
Clone this object
Reimplemented from OutputFunction.