#include <PDistributionVariable.h>
Inheritance diagram for PLearn::PDistributionVariable:
Public Types | |
| typedef UnaryVariable | inherited |
Public Member Functions | |
| PDistributionVariable () | |
| Default constructor for persistence. | |
| PDistributionVariable (Variable *no_noise_var, PP< PDistribution > this_dist) | |
| PLEARN_DECLARE_OBJECT (PDistributionVariable) | |
| virtual void | build () |
| Should call simply inherited::build(), then this class's build_(). | |
| virtual void | makeDeepCopyFromShallowCopy (map< const void *, void * > &copies) |
| 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 () |
Public Attributes | |
| PP< PDistribution > | dist |
Static Protected Member Functions | |
| void | declareOptions (OptionList &ol) |
| redefine this in subclasses: call declareOption(...) for each option, and then call inherited::declareOptions(options) ( see the declareOption function further down) | |
Private Member Functions | |
| void | build_ () |
|
|
Reimplemented from PLearn::UnaryVariable. Definition at line 56 of file PDistributionVariable.h. Referenced by PDistributionVariable(). |
|
|
Default constructor for persistence.
Definition at line 67 of file PDistributionVariable.h. |
|
||||||||||||
|
Definition at line 56 of file PDistributionVariable.cc. References PLearn::dist(), and 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 108 of file PDistributionVariable.cc. |
|
|
Implements PLearn::Variable. Definition at line 106 of file PDistributionVariable.cc. |
|
|
Should call simply inherited::build(), then this class's build_(). This method should be callable again at later times, after modifying some option fields to change the "architecture" of the object. Reimplemented from PLearn::Variable. Definition at line 83 of file PDistributionVariable.cc. References build_(). |
|
|
This method should be redefined in subclasses and do the actual building of the object according to previously set option fields. Constructors can just set option fields, and then call build_. This method is NOT virtual, and will typically be called only from three places: a constructor, the public virtual build() method, and possibly the public virtual read method (which calls its parent's read). build_() can assume that it's parent's build_ has already been called. Reimplemented from PLearn::Variable. Definition at line 89 of file PDistributionVariable.cc. References dist. Referenced by build(). |
|
|
redefine this in subclasses: call declareOption(...) for each option, and then call inherited::declareOptions(options) ( see the declareOption function further down) ex: static void declareOptions(OptionList& ol) { declareOption(ol, "inputsize", &MyObject::inputsize_, OptionBase::buildoption, "the size of the input\n it must be provided"); declareOption(ol, "weights", &MyObject::weights, OptionBase::learntoption, "the learnt model weights"); inherited::declareOptions(ol); } Reimplemented from PLearn::UnaryVariable. Definition at line 72 of file PDistributionVariable.cc. References PLearn::declareOption(), and PLearn::OptionList. |
|
|
compute output given input
Implements PLearn::Variable. Definition at line 101 of file PDistributionVariable.cc. References dist. |
|
|
Reimplemented from PLearn::UnaryVariable. Definition at line 94 of file PDistributionVariable.cc. References PLearn::deepCopyField(), and dist. |
|
|
|
|
||||||||||||
|
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 60 of file PDistributionVariable.cc. References PLearn::Var::length(), and PLearn::Var::width(). |
|
|
Reimplemented from PLearn::Variable. Definition at line 109 of file PDistributionVariable.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 110 of file PDistributionVariable.cc. |
|
|
Definition at line 57 of file PDistributionVariable.h. Referenced by build_(), fprop(), and makeDeepCopyFromShallowCopy(). |
1.3.7