shark::TanhNeuron Struct Reference

Neuron which computes the hyperbolic tangenst with range [-1,1]. 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 &) const

Detailed Description

Neuron which computes the hyperbolic tangenst with range [-1,1].

The Tanh function is

\[ f(x)=\tanh(x) = \frac 2 {1+exp^(-2x)}-1 \]

it's derivative can be computed as

\[ f'(x)= 1-f(x)^2 \]

Definition at line 44 of file NeuronLayers.h.

Member Typedef Documentation

State

typedef EmptyState shark::TanhNeuron::State

Definition at line 45 of file NeuronLayers.h.

Member Function Documentation

evalInPlace() [1/2]

template<class Arg >

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

inline

Definition at line 47 of file NeuronLayers.h.

Referenced by evalInPlace(), shark::LogisticNeuron::evalInPlace(), shark::FastSigmoidNeuron::evalInPlace(), shark::RectifierNeuron::evalInPlace(), and shark::SoftmaxNeuron< VectorType >::evalInPlace().

evalInPlace() [2/2]

template<class Arg >

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

inline

Definition at line 52 of file NeuronLayers.h.

References evalInPlace().

multiplyDerivative()

template<class Output , class Derivative >

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

inline

Definition at line 57 of file NeuronLayers.h.

---

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

• include/shark/Models/NeuronLayers.h