ActivationFunction
Description
Function used to activate neuron.
Values of this enumeration:
- Sigmoidal - \( f(x) = \frac{1}{1+e^{-x} }\)
- Linear - Saturated linear function. \( f(x) = \begin{cases} 1 & \text{if } x > 1 \\ 0 & \text{if } x < 0 \\ x & \text{otherwise} \end{cases}\)
- Tanh - \(f(x) = \tanh(x) = \frac{\exp(2x)-1}{\exp(2x)+1}\)
- Log - Logarithmic function.
- ArcTan - \( f(x) = \arctan(x)\)
- Gauss - \( f(x) = e^{-x^{2} }\)
- Elliot - \( f(x) = \frac{x}{1+|x|}+0.5\)
- Step - \( f(x) = \begin{cases} 1 & \text{if } x > 0 \\ 0 & \text{otherwise} \end{cases}\)
- FastSigmoidal - The same as Sigmoidal, but uses optimized exponent function.
- FastTanh - The same as Tanh, but uses optimized exponent function.