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

#include <ebl_nonlinearity.h>

Inheritance diagram for ebl::smooth_shrink_module< T, Tstate >:
ebl::module_1_1< T, Tstate > ebl::module

List of all members.

Public Member Functions

 smooth_shrink_module (parameter< T, Tstate > *p, intg nf, T beta=10, T bias=.3)
virtual ~smooth_shrink_module ()
 Destructor.
virtual void fprop (Tstate &in, Tstate &out)
 forward
virtual void bprop (Tstate &in, Tstate &out)
 backward
virtual void bbprop (Tstate &in, Tstate &out)
 2nd deriv backward
virtual smooth_shrink_module
< T, Tstate > * 
copy ()
 Returns a deep copy of this module.

Public Attributes

Tstate beta
Tstate bias

Detailed Description

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

A smoothed shrinkage module that parametrizes the steepnes and location of the shrinkage operator. This function is useful for learning since there is always gradients flowing through it.


Constructor & Destructor Documentation

template<typename T , class Tstate >
ebl::smooth_shrink_module< T, Tstate >::smooth_shrink_module ( parameter< T, Tstate > *  p,
intg  nf,
beta = 10,
bias = .3 
)

Constructor.

Parameters:
nfThe number of features.

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