class ClassNLLCriterion

This criterion can be used to train *in classification* a GradientMachine object using the StochasticGradient trainer.

Inheritance:

Public Methods
ClassNLLCriterion(ClassFormat* class_format): The ClassFormat is needed just to know how the targets are encoded in the dataset

Inherited from Criterion:

Public Fields
DataSet* data

Public Methods
virtual void setDataSet(DataSet* data_)

Inherited from GradientMachine:

Public Fields
int n_inputs
int n_outputs
Parameters* params
Parameters* der_params
Sequence* beta

Public Methods
virtual void iterInitialize()
virtual void forward(Sequence* inputs)
virtual void backward(Sequence* inputs, Sequence* alpha)
virtual void setPartialBackprop(bool flag=true)
virtual void frameForward(int t, real* f_inputs, real* f_outputs)
virtual void frameBackward(int t, real* f_inputs, real* beta_, real* f_outputs, real* alpha_)
virtual void loadXFile(XFile* file)
virtual void saveXFile(XFile* file)

Inherited from Machine:

Public Fields
Sequence* outputs

Public Methods
virtual void reset()

Inherited from Object:

Public Fields
Allocator* allocator

Public Methods
void addOption(const char* name, int size, void* ptr, const char* help="")
void addIOption(const char* name, int* ptr, int init_value, const char* help="")
void addROption(const char* name, real* ptr, real init_value, const char* help="")
void addBOption(const char* name, bool* ptr, bool init_value, const char* help="")
void addOOption(const char* name, Object** ptr, Object* init_value, const char* help="")
void setOption(const char* name, void* ptr)
void setIOption(const char* name, int option)
void setROption(const char* name, real option)
void setBOption(const char* name, bool option)
void setOOption(const char* name, Object* option)
void load(const char* filename)
void save(const char* filename)
void* operator new(size_t size, Allocator* allocator_=NULL)
void* operator new(size_t size, Allocator* allocator_, void* ptr_)
void operator delete(void* ptr)

Documentation

This criterion can be used to train *in classification* a GradientMachine object using the StochasticGradient trainer. It then maximizes the log likelihood of the data.
If we write for the output of the GradientMachine, it supposes that

the outputs are log-probabilities.
is the probability for the class
the predicted class follows a multinomial distribution with parameters

The number of target frames in DataSet must correspond to the number of input frames given to this criterion.