MiniDNN
Public Member Functions | List of all members
MiniDNN::Output Class Referenceabstract
Output Layers

#include <Output.h>

Inheritance diagram for MiniDNN::Output:
MiniDNN::BinaryClassEntropy MiniDNN::MultiClassEntropy MiniDNN::RegressionMSE

Public Member Functions

virtual void check_target_data (const Matrix &target)
 
virtual void check_target_data (const IntegerVector &target)
 
virtual void evaluate (const Matrix &prev_layer_data, const Matrix &target)=0
 
virtual void evaluate (const Matrix &prev_layer_data, const IntegerVector &target)
 
virtual const Matrix & backprop_data () const =0
 
virtual Scalar loss () const =0
 

Detailed Description

The interface of the output layer of a neural network model. The output layer is a special layer that associates the last hidden layer with the target response variable.

Definition at line 22 of file Output.h.

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