Normalizes the sum of inputs to one. More...
#include <shark/Models/NeuronLayers.h>
| Classes | |
| struct | State | 
| Public Member Functions | |
| template<class Arg , class Device > | |
| void | evalInPlace (blas::vector_expression< Arg, Device > &arg) const | 
| template<class Arg , class Device > | |
| void | evalInPlace (blas::matrix_expression< Arg, Device > &arg) const | 
| template<class Arg , class Device > | |
| void | evalInPlace (blas::matrix_expression< Arg, Device > &arg, State &state) const | 
| template<class Output , class Derivative > | |
| void | multiplyDerivative (Output const &output, Derivative &der, State const &s) const | 
Normalizes the sum of inputs to one.
\[ f_i(x)= x_i \ \sum_j x_j \]
Normalization will reinterpret the input as probabilities. Therefore no negative valeus are allowed.
Definition at line 174 of file NeuronLayers.h.
| 
 | inline | 
Definition at line 189 of file NeuronLayers.h.
| 
 | inline | 
Definition at line 194 of file NeuronLayers.h.
References shark::NormalizerNeuron< VectorType >::State::norm.
| 
 | inline | 
Definition at line 184 of file NeuronLayers.h.
| 
 | inline | 
Definition at line 201 of file NeuronLayers.h.
References shark::NormalizerNeuron< VectorType >::State::norm.