GRLNeuro Class Reference

Class to represent the GRL Neuro. More...

#include <GRLNeuro.h>

Collaboration diagram for GRLNeuro:

Classes
struct	Parameters
	Struct to keep neurotrigger parameters. More...

Public Member Functions
	GRLNeuro ()
	Default constructor.
virtual	~GRLNeuro ()
	Default destructor.
void	initialize (const Parameters &p)
	Set parameters and get some network independent parameters.
void	save (const std::string &filename, const std::string &arrayname="MLPs")
	Save MLPs to file. More...
bool	load (const std::string &filename, const std::string &arrayname="MLPs")
	Load MLPs from file. More...
void	setPrecision (const std::vector< unsigned > &precision)
	Loads parameters from the geometry and precalculates some constants that will be needed. More...
GRLMLP &	operator[] (unsigned index)
	set the hit collection and event time to required and store the hit collection name More...
const GRLMLP &	operator[] (unsigned index) const
	return const reference to a neural network
unsigned	nSectors () const
	return number of neural networks
void	addMLP (const GRLMLP &newMLP)
	add an MLP to the list of networks
std::vector< float >	runMLP (unsigned isector, const std::vector< float > &input)
	Run an expert MLP. More...
std::vector< float >	runMLPFix (unsigned isector, const std::vector< float > &input)
	Run an expert MLP with fixed point arithmetic.

Private Attributes
std::vector< GRLMLP >	m_MLPs = {}
	List of networks.
std::vector< unsigned >	m_precision
	Fixed point precision in bit after radix point. More...

Detailed Description

Class to represent the GRL Neuro.

The Neurotrigger consists of one or several Multi Layer Perceptrons. The input values are calculated from ECLTRG cluster and a 2D track estimate. The output is a scaled estimate of the judgement.

See also

GRLNeuro Modules:

GRLTrainerModule for preparing training data and training,

GRLNeuro for loading trained networks and using them.

Definition at line 27 of file GRLNeuro.h.

Member Function Documentation

load()

bool load	(	const std::string &	filename,
		const std::string &	arrayname = "MLPs"
	)

Load MLPs from file.

Parameters

filename	name of the TFile to read from
arrayname	name of the TObjArray holding the MLPs in the file

Returns

true if the MLPs were loaded correctly

operator[]()

GRLMLP& operator[] ( unsigned  index )

inline

set the hit collection and event time to required and store the hit collection name

return reference to a neural network

Definition at line 93 of file GRLNeuro.h.

{ return m_MLPs[index]; }

runMLP()

vector< float > runMLP	(	unsigned	isector,
		const std::vector< float > &	input
	)

Run an expert MLP.

Parameters

isector	index of the MLP
input	vector of input values

Returns

unscaled output values (z vertex in cm and/or theta in radian)

Definition at line 106 of file GRLNeuro.cc.

{
  const GRLMLP& expert = m_MLPs[isector];
  vector<float> weights = expert.getWeights();
  vector<float> layerinput = input;
  vector<float> layeroutput = {};
  unsigned iw = 0;
  for (unsigned il = 1; il < expert.nLayers(); ++il) {
    //add bias input
    layerinput.push_back(1.);
    //prepare output
    layeroutput.clear();
    layeroutput.assign(expert.nNodesLayer(il), 0.);
    //loop over outputs
    for (unsigned io = 0; io < layeroutput.size(); ++io) {
      //loop over inputs
      for (unsigned ii = 0; ii < layerinput.size(); ++ii) {
        layeroutput[io] += layerinput[ii] * weights[iw++];
      }
      //apply activation function
      layeroutput[io] = tanh(layeroutput[io] / 2.);
    }
    //output is new input
    layerinput = layeroutput;
  }
  return layeroutput;
}

save()

void save	(	const std::string &	filename,
		const std::string &	arrayname = "MLPs"
	)

Save MLPs to file.

Parameters

filename	name of the TFile to write to
arrayname	name of the TObjArray holding the MLPs in the file

Definition at line 195 of file GRLNeuro.cc.

setPrecision()

void setPrecision ( const std::vector< unsigned > &  precision )

inline

Loads parameters from the geometry and precalculates some constants that will be needed.

set fixed point precision

Definition at line 86 of file GRLNeuro.h.

Member Data Documentation

m_precision

std::vector<unsigned> m_precision

private

Fixed point precision in bit after radix point.

8 values:

• 2D track parameters: omega, phi
• geometrical values derived from track: crossing angle, reference wire ID
• scale factor: radian to wire ID
• MLP values: nodes, weights, activation function LUT input (LUT output = nodes)

Definition at line 122 of file GRLNeuro.h.

---

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

• trg/grl/include/GRLNeuro.h
• trg/grl/src/GRLNeuro.cc