 |
Belle II Software
release-05-01-25
|
5 #include <framework/logging/Logger.h>
23 GRLMLP(std::vector<unsigned short>& nodes,
unsigned short targets,
const std::vector<float>& outputscale);
The trainer module for the neural networks of the CDC trigger.
unsigned nWeights() const
get number of weights from length of weights vector
std::vector< float > weights
Weights of the network.
std::vector< unsigned short > nNodes
Number of nodes in each layer, not including bias nodes.
~GRLMLP()
destructor, empty because we don't allocate memory anywhere.
Class to keep all parameters of an expert MLP for the neuro trigger.
bool trained
Indicator whether the weights are just default values or have been set by some trainer (set to true w...
GRLMLP()
default constructor.
bool isTrained() const
check if weights are default values or set by some trainer
ClassDef(GRLMLP, 2)
Needed to make the ROOT object storable.
std::vector< float > outputScale
Output[i] of the MLP is scaled from [-1, 1] to [outputScale[2i], outputScale[2i+1]].
Abstract base class for different kinds of events.
unsigned nLayers() const
get number of layers
unsigned nNodesLayer(unsigned iLayer) const
get number of nodes in a layer
std::vector< float > getWeights() const
get weights vector
unsigned nWeightsCal() const
calculate number of weights from number of nodes
unsigned short targetVars
output variables: 1: z, 2: theta, 3: (z, theta)