Interface | Description |
---|---|
ActivationFunction |
This interface allows various activation functions to be used with the neural
network.
|
Class | Description |
---|---|
ActivationBiPolar |
BiPolar activation function.
|
ActivationBipolarSteepenedSigmoid |
The bipolar sigmoid activation function is like the regular sigmoid activation function,
except Bipolar sigmoid activation function.
|
ActivationClippedLinear |
Linear activation function that bounds the output to [-1,+1].
|
ActivationCompetitive |
An activation function that only allows a specified number, usually one, of
the out-bound connection to win.
|
ActivationElliott |
Computationally efficient alternative to ActivationSigmoid.
|
ActivationElliottSymmetric |
Computationally efficient alternative to ActivationTANH.
|
ActivationGaussian |
An activation function based on the Gaussian function.
|
ActivationLinear |
The Linear layer is really not an activation function at all.
|
ActivationLOG |
An activation function based on the logarithm function.
|
ActivationRamp |
A ramp activation function.
|
ActivationSigmoid |
The sigmoid activation function takes on a sigmoidal shape.
|
ActivationSIN |
An activation function based on the sin function, with a double period.
|
ActivationSoftMax |
The softmax activation function.
|
ActivationSteepenedSigmoid |
The Steepened Sigmoid is an activation function typically used with NEAT.
|
ActivationStep |
The step activation function is a very simple activation function.
|
ActivationTANH |
The hyperbolic tangent activation function takes the curved shape of the
hyperbolic tangent.
|
Copyright © 2014. All Rights Reserved.