shark::LogisticNeuron Struct Reference

Neuron which computes the Logistic (logistic) function with range [0,1]. More...

#include <shark/Models/NeuronLayers.h>

Public Types
typedef EmptyState	State

Public Member Functions
template<class Arg >
void	evalInPlace (Arg &arg) const
template<class Arg >
void	evalInPlace (Arg &arg, State &) const
template<class Output , class Derivative >
void	multiplyDerivative (Output const &output, Derivative &der, State const &state) const

Detailed Description

Neuron which computes the Logistic (logistic) function with range [0,1].

The Logistic function is

\[ f(x)=\frac 1 {1+exp^(-x)}\]

it's derivative can be computed as

\[ f'(x)= f(x)(1-f(x)) \]

Definition at line 78 of file NeuronLayers.h.

Member Typedef Documentation

State

typedef EmptyState shark::LogisticNeuron::State

Definition at line 79 of file NeuronLayers.h.

Member Function Documentation

evalInPlace() [1/2]

template<class Arg >

void shark::LogisticNeuron::evalInPlace ( Arg &  arg ) const

inline

Definition at line 81 of file NeuronLayers.h.

References shark::sigmoid().

Referenced by evalInPlace().

evalInPlace() [2/2]

template<class Arg >

void shark::LogisticNeuron::evalInPlace ( Arg &  arg, State &    ) const

inline

Definition at line 86 of file NeuronLayers.h.

References evalInPlace().

multiplyDerivative()

template<class Output , class Derivative >

void shark::LogisticNeuron::multiplyDerivative ( Output const &  output, Derivative &  der, State const &  state  ) const

inline

Definition at line 91 of file NeuronLayers.h.

---

The documentation for this struct was generated from the following file:

• include/shark/Models/NeuronLayers.h