#include <MatrixSoftmaxVariable.h>
Inheritance diagram for PLearn::MatrixSoftmaxVariable:
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 |
|
Reimplemented from PLearn::UnaryVariable. Definition at line 54 of file MatrixSoftmaxVariable.h. Referenced by MatrixSoftmaxVariable(). |
|
Default constructor for persistence.
Definition at line 58 of file MatrixSoftmaxVariable.h. |
|
Definition at line 55 of file MatrixSoftmaxVariable.cc. References inherited. |
|
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. |
|
Implements PLearn::Variable. Definition at line 88 of file MatrixSoftmaxVariable.cc. References k, PLearn::Variable::length(), PLearn::Var::length(), and PLearn::Var::width(). |
|
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(). |
|
|
|
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(). |
|
Reimplemented from PLearn::Variable. Definition at line 118 of file MatrixSoftmaxVariable.cc. References PLERROR. |
|
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. |