Function fitter using contrastive divergence algorithm.
You can connect as many input slots as training data as needed. Activate addMirrored to make sure that the training data are symmetric (this adds the trainig data inverted).
input slots | |
| InputSlot< CDFitFunction * > | toFit |
| function to train | |
| InputSlot< CImgList< T > > | training |
| training data input | |
output slots | |
parameters | |
| Parameter< bool > | addMirrored |
| add mirrored training data | |
| Parameter< double > | agressiveness |
| control update cycle | |
| Parameter< double > | agStop |
| stop threshold for agressiveness | |
| Parameter< double > | cooldown |
| agressiveness reduction ratio | |
| Parameter< std::string > | gnuplotCall |
| gnuplot call | |
| Parameter< double > | mcmcSigma |
| mcmc noise sigma | |
| Parameter< unsigned int > | mcmcSweeps |
| mcmc sweeps during one update cycle | |
| Parameter< unsigned int > | oscis |
| number of oscillations for detection | |
| Parameter< std::string > | results |
| results output | |
| Parameter< unsigned int > | runs |
| number of dc cycles | |
| Parameter< bool > | showHistogram |
| show histogram and current status | |
| Parameter< bool > | showProgress |
| progress display using gnuplot | |
This Module subclasses TemplatedParameteredObject< T >.
For documentation of parameters and slots inherited by this base class,
please have a look at the corresponding Module reference.
This module is templated. There are instances with T=int,float,double.
An additional parameter called templatetype
may be used to select which instantiation you want.
The detailed doxygen documentation beyond the parameters/slots may be found here.