Enum ActivationFunction
- All Implemented Interfaces:
Serializable
,Comparable<ActivationFunction>
,Constable
public enum ActivationFunction extends Enum<ActivationFunction>
This enum represents the available activation functions f: Rn→
Rn for use with neural networks. Use the
get(ArrayList,
ActivationFunction)
or getDerivative(ArrayList, ArrayList,
ActivationFunction)
to get computations for the function and the derivative resp.-
Nested Class Summary
-
Enum Constant Summary
-
Method Summary
Modifier and Type Method Description static Computation<ArrayList<DRes<SFixed>>,ProtocolBuilderNumeric>
get(ArrayList<DRes<SFixed>> x, ActivationFunction type)
static Computation<ArrayList<DRes<SFixed>>,ProtocolBuilderNumeric>
getDerivative(ArrayList<DRes<SFixed>> x, ArrayList<DRes<SFixed>> y, ActivationFunction type)
Compute f'(x) for the given activation function f: Rn → Rn.static ActivationFunction
valueOf(String name)
Returns the enum constant of this type with the specified name.static ActivationFunction[]
values()
Returns an array containing the constants of this enum type, in the order they are declared.
-
Enum Constant Details
-
Method Details
-
values
Returns an array containing the constants of this enum type, in the order they are declared.- Returns:
- an array containing the constants of this enum type, in the order they are declared
-
valueOf
Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)- Parameters:
name
- the name of the enum constant to be returned.- Returns:
- the enum constant with the specified name
- Throws:
IllegalArgumentException
- if this enum type has no constant with the specified nameNullPointerException
- if the argument is null
-
get
public static Computation<ArrayList<DRes<SFixed>>,ProtocolBuilderNumeric> get(ArrayList<DRes<SFixed>> x, ActivationFunction type) -
getDerivative
public static Computation<ArrayList<DRes<SFixed>>,ProtocolBuilderNumeric> getDerivative(ArrayList<DRes<SFixed>> x, ArrayList<DRes<SFixed>> y, ActivationFunction type)Compute f'(x) for the given activation function f: Rn → Rn. The function value y = f(x) may be used in the computation if it makes the computation easier for the given function.
-