PLearn::MatrixSoftmaxVariable Class Reference

#include <MatrixSoftmaxVariable.h>

Inheritance diagram for PLearn::MatrixSoftmaxVariable:

[legend]Collaboration diagram for PLearn::MatrixSoftmaxVariable:

[legend]List of all members.

Public Member Functions
	MatrixSoftmaxVariable ()
	Default constructor for persistence.
	MatrixSoftmaxVariable (Variable *input)
	PLEARN_DECLARE_OBJECT (MatrixSoftmaxVariable)
virtual void	recomputeSize (int &l, int &w) const
	Recomputes the length l and width w that this variable should have, according to its parent variables.
virtual void	fprop ()
	compute output given input
virtual void	bprop ()
virtual void	bbprop ()
	compute an approximation to diag(d^2/dinput^2) given diag(d^2/doutput^2), with diag(d^2/dinput^2) ~=~ (doutput/dinput)' diag(d^2/doutput^2) (doutput/dinput) In particular: if 'C' depends on 'y' and 'y' depends on x ...
virtual void	symbolicBprop ()
	compute a piece of new Var graph that represents the symbolic derivative of this Var
virtual void	rfprop ()
Private Types
typedef UnaryVariable	inherited

---

Member Typedef Documentation

typedef UnaryVariable PLearn::MatrixSoftmaxVariable::inherited [private]

Reimplemented from PLearn::UnaryVariable. Definition at line 54 of file MatrixSoftmaxVariable.h. Referenced by MatrixSoftmaxVariable().

---

Constructor & Destructor Documentation

PLearn::MatrixSoftmaxVariable::MatrixSoftmaxVariable (   )  [inline]

Default constructor for persistence. Definition at line 58 of file MatrixSoftmaxVariable.h.

PLearn::MatrixSoftmaxVariable::MatrixSoftmaxVariable (  Variable *  input  )

Definition at line 55 of file MatrixSoftmaxVariable.cc. References inherited.

---

Member Function Documentation

void PLearn::MatrixSoftmaxVariable::bbprop (   )  [virtual]

compute an approximation to diag(d^2/dinput^2) given diag(d^2/doutput^2), with diag(d^2/dinput^2) ~=~ (doutput/dinput)' diag(d^2/doutput^2) (doutput/dinput) In particular: if 'C' depends on 'y' and 'y' depends on x ... d^2C/dx^2 = d^2C/dy^2 * (dy/dx)^2 + dC/dy * d^2y/dx^2 (diaghessian) (gradient) Reimplemented from PLearn::Variable. Definition at line 105 of file MatrixSoftmaxVariable.cc. References PLERROR.

void PLearn::MatrixSoftmaxVariable::bprop (   )  [virtual]

Implements PLearn::Variable. Definition at line 88 of file MatrixSoftmaxVariable.cc. References k, PLearn::Variable::length(), PLearn::Var::length(), and PLearn::Var::width().

void PLearn::MatrixSoftmaxVariable::fprop (   )  [virtual]

compute output given input Implements PLearn::Variable. Definition at line 69 of file MatrixSoftmaxVariable.cc. References PLearn::columnMax(), PLearn::Var::length(), PLERROR, PLearn::safeexp(), PLearn::Vec, PLearn::Var::width(), and PLearn::Variable::width().

PLearn::MatrixSoftmaxVariable::PLEARN_DECLARE_OBJECT (  MatrixSoftmaxVariable   )

void PLearn::MatrixSoftmaxVariable::recomputeSize (  int &  l, int &  w )  const [virtual]

Recomputes the length l and width w that this variable should have, according to its parent variables. This is used for ex. by sizeprop() The default version stupidly returns the current dimensions, so make sure to overload it in subclasses if this is not appropriate. Reimplemented from PLearn::Variable. Definition at line 59 of file MatrixSoftmaxVariable.cc. References PLearn::Var::length(), and PLearn::Var::width().

void PLearn::MatrixSoftmaxVariable::rfprop (   )  [virtual]

Reimplemented from PLearn::Variable. Definition at line 118 of file MatrixSoftmaxVariable.cc. References PLERROR.

void PLearn::MatrixSoftmaxVariable::symbolicBprop (   )  [virtual]

compute a piece of new Var graph that represents the symbolic derivative of this Var Reimplemented from PLearn::Variable. Definition at line 111 of file MatrixSoftmaxVariable.cc. References PLERROR.

---

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

• MatrixSoftmaxVariable.h
• MatrixSoftmaxVariable.cc

---