libeblearn
ebl::cross_entropy_energy< T, Tstate > Class Template Reference

#include <ebl_energy.h>

Inheritance diagram for ebl::cross_entropy_energy< T, Tstate >:
ebl::ebm_2< Tstate > ebl::module

List of all members.

Public Member Functions

 cross_entropy_energy (const char *name="cross_entropy_energy")
virtual void fprop (Tstate &in1, Tstate &in2, Tstate &energy)
 fprop: compute output from input
virtual void bprop (Tstate &in1, Tstate &in2, Tstate &energy)
 bprop: compute gradient wrt inputs, given gradient wrt output
virtual void bbprop (Tstate &in1, Tstate &in2, Tstate &energy)
 bprop: compute diaghession wrt inputs, given diaghessian wrt output
virtual void infer2_copy (Tstate &i1, Tstate &i2, Tstate &energy)
virtual std::string describe ()
 Returns a string describing this module and its parameters.

Protected Attributes

idx< T > tmp
 Buffer for temporary operations.

Detailed Description

template<typename T, class Tstate = bbstate_idx<T>>
class ebl::cross_entropy_energy< T, Tstate >

A cross-entropy energy module for multinomiol logistic regression. Energy equals: - desired where desired is a 1-of-n encoding of the groundtruth class.


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