/*************************************************************************
Like MLPCreate0, but for ensembles.
-- ALGLIB --
Copyright 18.02.2009 by Bochkanov Sergey
*************************************************************************/
public static void mlpecreate0(int nin,
int nout,
int ensemblesize,
ref mlpensemble ensemble)
{
mlpbase.multilayerperceptron net = new mlpbase.multilayerperceptron();
mlpbase.mlpcreate0(nin, nout, ref net);
mlpecreatefromnetwork(ref net, ensemblesize, ref ensemble);
}
/*************************************************************************
Like MLPCreateR2, but for ensembles.
-- ALGLIB --
Copyright 18.02.2009 by Bochkanov Sergey
*************************************************************************/
public static void mlpecreater2(int nin,
int nhid1,
int nhid2,
int nout,
double a,
double b,
int ensemblesize,
ref mlpensemble ensemble)
{
mlpbase.multilayerperceptron net = new mlpbase.multilayerperceptron();
mlpbase.mlpcreater2(nin, nhid1, nhid2, nout, a, b, ref net);
mlpecreatefromnetwork(ref net, ensemblesize, ref ensemble);
}
/*************************************************************************
Internal cross-validation subroutine
*************************************************************************/
private static void mlpkfoldcvgeneral(ref mlpbase.multilayerperceptron n,
ref double[,] xy,
int npoints,
double decay,
int restarts,
int foldscount,
bool lmalgorithm,
double wstep,
int maxits,
ref int info,
ref mlpreport rep,
ref mlpcvreport cvrep)
{
int i = 0;
int fold = 0;
int j = 0;
int k = 0;
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
int nin = 0;
int nout = 0;
int rowlen = 0;
int wcount = 0;
int nclasses = 0;
int tssize = 0;
int cvssize = 0;
double[,] cvset = new double[0,0];
double[,] testset = new double[0,0];
int[] folds = new int[0];
int relcnt = 0;
mlpreport internalrep = new mlpreport();
double[] x = new double[0];
double[] y = new double[0];
int i_ = 0;
//
// Read network geometry, test parameters
//
mlpbase.mlpproperties(ref n, ref nin, ref nout, ref wcount);
if( mlpbase.mlpissoftmax(ref n) )
{
nclasses = nout;
rowlen = nin+1;
}
else
{
nclasses = -nout;
rowlen = nin+nout;
}
if( npoints<=0 | foldscount<2 | foldscount>npoints )
{
info = -1;
return;
}
mlpbase.mlpcopy(ref n, ref network);
//
// K-fold out cross-validation.
// First, estimate generalization error
//
testset = new double[npoints-1+1, rowlen-1+1];
cvset = new double[npoints-1+1, rowlen-1+1];
x = new double[nin-1+1];
y = new double[nout-1+1];
mlpkfoldsplit(ref xy, npoints, nclasses, foldscount, false, ref folds);
cvrep.relclserror = 0;
cvrep.avgce = 0;
cvrep.rmserror = 0;
cvrep.avgerror = 0;
cvrep.avgrelerror = 0;
rep.ngrad = 0;
rep.nhess = 0;
rep.ncholesky = 0;
relcnt = 0;
for(fold=0; fold<=foldscount-1; fold++)
{
//
// Separate set
//
tssize = 0;
cvssize = 0;
for(i=0; i<=npoints-1; i++)
{
if( folds[i]==fold )
{
for(i_=0; i_<=rowlen-1;i_++)
{
testset[tssize,i_] = xy[i,i_];
}
tssize = tssize+1;
}
else
{
for(i_=0; i_<=rowlen-1;i_++)
{
cvset[cvssize,i_] = xy[i,i_];
}
cvssize = cvssize+1;
}
}
//
// Train on CV training set
//
if( lmalgorithm )
{
mlptrainlm(ref network, ref cvset, cvssize, decay, restarts, ref info, ref internalrep);
}
else
{
mlptrainlbfgs(ref network, ref cvset, cvssize, decay, restarts, wstep, maxits, ref info, ref internalrep);
}
if( info<0 )
{
cvrep.relclserror = 0;
cvrep.avgce = 0;
cvrep.rmserror = 0;
cvrep.avgerror = 0;
cvrep.avgrelerror = 0;
return;
}
rep.ngrad = rep.ngrad+internalrep.ngrad;
rep.nhess = rep.nhess+internalrep.nhess;
rep.ncholesky = rep.ncholesky+internalrep.ncholesky;
//
// Estimate error using CV test set
//
if( mlpbase.mlpissoftmax(ref network) )
{
//
// classification-only code
//
cvrep.relclserror = cvrep.relclserror+mlpbase.mlpclserror(ref network, ref testset, tssize);
cvrep.avgce = cvrep.avgce+mlpbase.mlperrorn(ref network, ref testset, tssize);
}
for(i=0; i<=tssize-1; i++)
{
for(i_=0; i_<=nin-1;i_++)
{
x[i_] = testset[i,i_];
}
mlpbase.mlpprocess(ref network, ref x, ref y);
if( mlpbase.mlpissoftmax(ref network) )
{
//
// Classification-specific code
//
k = (int)Math.Round(testset[i,nin]);
for(j=0; j<=nout-1; j++)
{
if( j==k )
{
cvrep.rmserror = cvrep.rmserror+AP.Math.Sqr(y[j]-1);
cvrep.avgerror = cvrep.avgerror+Math.Abs(y[j]-1);
cvrep.avgrelerror = cvrep.avgrelerror+Math.Abs(y[j]-1);
relcnt = relcnt+1;
}
else
{
cvrep.rmserror = cvrep.rmserror+AP.Math.Sqr(y[j]);
cvrep.avgerror = cvrep.avgerror+Math.Abs(y[j]);
}
}
}
else
{
//
// Regression-specific code
//
for(j=0; j<=nout-1; j++)
{
cvrep.rmserror = cvrep.rmserror+AP.Math.Sqr(y[j]-testset[i,nin+j]);
cvrep.avgerror = cvrep.avgerror+Math.Abs(y[j]-testset[i,nin+j]);
if( (double)(testset[i,nin+j])!=(double)(0) )
{
cvrep.avgrelerror = cvrep.avgrelerror+Math.Abs((y[j]-testset[i,nin+j])/testset[i,nin+j]);
relcnt = relcnt+1;
}
}
}
}
}
if( mlpbase.mlpissoftmax(ref network) )
{
cvrep.relclserror = cvrep.relclserror/npoints;
cvrep.avgce = cvrep.avgce/(Math.Log(2)*npoints);
}
cvrep.rmserror = Math.Sqrt(cvrep.rmserror/(npoints*nout));
cvrep.avgerror = cvrep.avgerror/(npoints*nout);
cvrep.avgrelerror = cvrep.avgrelerror/relcnt;
info = 1;
}
/*************************************************************************
Internal bagging subroutine.
-- ALGLIB --
Copyright 19.02.2009 by Bochkanov Sergey
*************************************************************************/
private static void mlpebagginginternal(ref mlpensemble ensemble,
ref double[,] xy,
int npoints,
double decay,
int restarts,
double wstep,
int maxits,
bool lmalgorithm,
ref int info,
ref mlptrain.mlpreport rep,
ref mlptrain.mlpcvreport ooberrors)
{
double[,] xys = new double[0,0];
bool[] s = new bool[0];
double[,] oobbuf = new double[0,0];
int[] oobcntbuf = new int[0];
double[] x = new double[0];
double[] y = new double[0];
double[] dy = new double[0];
double[] dsbuf = new double[0];
int nin = 0;
int nout = 0;
int ccnt = 0;
int pcnt = 0;
int i = 0;
int j = 0;
int k = 0;
double v = 0;
mlptrain.mlpreport tmprep = new mlptrain.mlpreport();
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
int i_ = 0;
int i1_ = 0;
//
// Test for inputs
//
if( !lmalgorithm & (double)(wstep)==(double)(0) & maxits==0 )
{
info = -8;
return;
}
if( npoints<=0 | restarts<1 | (double)(wstep)<(double)(0) | maxits<0 )
{
info = -1;
return;
}
if( ensemble.issoftmax )
{
for(i=0; i<=npoints-1; i++)
{
if( (int)Math.Round(xy[i,ensemble.nin])<0 | (int)Math.Round(xy[i,ensemble.nin])>=ensemble.nout )
{
info = -2;
return;
}
}
}
//
// allocate temporaries
//
info = 2;
rep.ngrad = 0;
rep.nhess = 0;
rep.ncholesky = 0;
ooberrors.relclserror = 0;
ooberrors.avgce = 0;
ooberrors.rmserror = 0;
ooberrors.avgerror = 0;
ooberrors.avgrelerror = 0;
nin = ensemble.nin;
nout = ensemble.nout;
if( ensemble.issoftmax )
{
ccnt = nin+1;
pcnt = nin;
}
else
{
ccnt = nin+nout;
pcnt = nin+nout;
}
xys = new double[npoints-1+1, ccnt-1+1];
s = new bool[npoints-1+1];
oobbuf = new double[npoints-1+1, nout-1+1];
oobcntbuf = new int[npoints-1+1];
x = new double[nin-1+1];
y = new double[nout-1+1];
if( ensemble.issoftmax )
{
dy = new double[0+1];
}
else
{
dy = new double[nout-1+1];
}
for(i=0; i<=npoints-1; i++)
{
for(j=0; j<=nout-1; j++)
{
oobbuf[i,j] = 0;
}
}
for(i=0; i<=npoints-1; i++)
{
oobcntbuf[i] = 0;
}
mlpbase.mlpunserialize(ref ensemble.serializedmlp, ref network);
//
// main bagging cycle
//
for(k=0; k<=ensemble.ensemblesize-1; k++)
{
//
// prepare dataset
//
for(i=0; i<=npoints-1; i++)
{
s[i] = false;
}
for(i=0; i<=npoints-1; i++)
{
j = AP.Math.RandomInteger(npoints);
s[j] = true;
for(i_=0; i_<=ccnt-1;i_++)
{
xys[i,i_] = xy[j,i_];
}
}
//
// train
//
if( lmalgorithm )
{
mlptrain.mlptrainlm(ref network, ref xys, npoints, decay, restarts, ref info, ref tmprep);
}
else
{
mlptrain.mlptrainlbfgs(ref network, ref xys, npoints, decay, restarts, wstep, maxits, ref info, ref tmprep);
}
if( info<0 )
{
return;
}
//
// save results
//
rep.ngrad = rep.ngrad+tmprep.ngrad;
rep.nhess = rep.nhess+tmprep.nhess;
rep.ncholesky = rep.ncholesky+tmprep.ncholesky;
i1_ = (0) - (k*ensemble.wcount);
for(i_=k*ensemble.wcount; i_<=(k+1)*ensemble.wcount-1;i_++)
{
ensemble.weights[i_] = network.weights[i_+i1_];
}
i1_ = (0) - (k*pcnt);
for(i_=k*pcnt; i_<=(k+1)*pcnt-1;i_++)
{
ensemble.columnmeans[i_] = network.columnmeans[i_+i1_];
}
i1_ = (0) - (k*pcnt);
for(i_=k*pcnt; i_<=(k+1)*pcnt-1;i_++)
{
ensemble.columnsigmas[i_] = network.columnsigmas[i_+i1_];
}
//
// OOB estimates
//
for(i=0; i<=npoints-1; i++)
{
if( !s[i] )
{
for(i_=0; i_<=nin-1;i_++)
{
x[i_] = xy[i,i_];
}
mlpbase.mlpprocess(ref network, ref x, ref y);
for(i_=0; i_<=nout-1;i_++)
{
oobbuf[i,i_] = oobbuf[i,i_] + y[i_];
}
oobcntbuf[i] = oobcntbuf[i]+1;
}
}
}
//
// OOB estimates
//
if( ensemble.issoftmax )
{
bdss.dserrallocate(nout, ref dsbuf);
}
else
{
bdss.dserrallocate(-nout, ref dsbuf);
}
for(i=0; i<=npoints-1; i++)
{
if( oobcntbuf[i]!=0 )
{
v = (double)(1)/(double)(oobcntbuf[i]);
for(i_=0; i_<=nout-1;i_++)
{
y[i_] = v*oobbuf[i,i_];
}
if( ensemble.issoftmax )
{
dy[0] = xy[i,nin];
}
else
{
i1_ = (nin) - (0);
for(i_=0; i_<=nout-1;i_++)
{
dy[i_] = v*xy[i,i_+i1_];
}
}
bdss.dserraccumulate(ref dsbuf, ref y, ref dy);
}
}
bdss.dserrfinish(ref dsbuf);
ooberrors.relclserror = dsbuf[0];
ooberrors.avgce = dsbuf[1];
ooberrors.rmserror = dsbuf[2];
ooberrors.avgerror = dsbuf[3];
ooberrors.avgrelerror = dsbuf[4];
}
/*************************************************************************
This subroutine trains logit model.
INPUT PARAMETERS:
XY - training set, array[0..NPoints-1,0..NVars]
First NVars columns store values of independent
variables, next column stores number of class (from 0
to NClasses-1) which dataset element belongs to. Fractional
values are rounded to nearest integer.
NPoints - training set size, NPoints>=1
NVars - number of independent variables, NVars>=1
NClasses - number of classes, NClasses>=2
OUTPUT PARAMETERS:
Info - return code:
* -2, if there is a point with class number
outside of [0..NClasses-1].
* -1, if incorrect parameters was passed
(NPoints<NVars+2, NVars<1, NClasses<2).
* 1, if task has been solved
LM - model built
Rep - training report
-- ALGLIB --
Copyright 10.09.2008 by Bochkanov Sergey
*************************************************************************/
public static void mnltrainh(ref double[,] xy,
int npoints,
int nvars,
int nclasses,
ref int info,
ref logitmodel lm,
ref mnlreport rep)
{
int i = 0;
int j = 0;
int k = 0;
int ssize = 0;
bool allsame = new bool();
int offs = 0;
double threshold = 0;
double wminstep = 0;
double decay = 0;
int wdim = 0;
int expoffs = 0;
double v = 0;
double s = 0;
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
int nin = 0;
int nout = 0;
int wcount = 0;
double e = 0;
double[] g = new double[0];
double[,] h = new double[0,0];
bool spd = new bool();
double[] x = new double[0];
double[] y = new double[0];
double[] wbase = new double[0];
double wstep = 0;
double[] wdir = new double[0];
double[] work = new double[0];
int mcstage = 0;
logitmcstate mcstate = new logitmcstate();
int mcinfo = 0;
int mcnfev = 0;
int solverinfo = 0;
densesolver.densesolverreport solverrep = new densesolver.densesolverreport();
int i_ = 0;
int i1_ = 0;
threshold = 1000*AP.Math.MachineEpsilon;
wminstep = 0.001;
decay = 0.001;
//
// Test for inputs
//
if( npoints<nvars+2 | nvars<1 | nclasses<2 )
{
info = -1;
return;
}
for(i=0; i<=npoints-1; i++)
{
if( (int)Math.Round(xy[i,nvars])<0 | (int)Math.Round(xy[i,nvars])>=nclasses )
{
info = -2;
return;
}
}
info = 1;
//
// Initialize data
//
rep.ngrad = 0;
rep.nhess = 0;
//
// Allocate array
//
wdim = (nvars+1)*(nclasses-1);
offs = 5;
expoffs = offs+wdim;
ssize = 5+(nvars+1)*(nclasses-1)+nclasses;
lm.w = new double[ssize-1+1];
lm.w[0] = ssize;
lm.w[1] = logitvnum;
lm.w[2] = nvars;
lm.w[3] = nclasses;
lm.w[4] = offs;
//
// Degenerate case: all outputs are equal
//
allsame = true;
for(i=1; i<=npoints-1; i++)
{
if( (int)Math.Round(xy[i,nvars])!=(int)Math.Round(xy[i-1,nvars]) )
{
allsame = false;
}
}
if( allsame )
{
for(i=0; i<=(nvars+1)*(nclasses-1)-1; i++)
{
lm.w[offs+i] = 0;
}
v = -(2*Math.Log(AP.Math.MinRealNumber));
k = (int)Math.Round(xy[0,nvars]);
if( k==nclasses-1 )
{
for(i=0; i<=nclasses-2; i++)
{
lm.w[offs+i*(nvars+1)+nvars] = -v;
}
}
else
{
for(i=0; i<=nclasses-2; i++)
{
if( i==k )
{
lm.w[offs+i*(nvars+1)+nvars] = +v;
}
else
{
lm.w[offs+i*(nvars+1)+nvars] = 0;
}
}
}
return;
}
//
// General case.
// Prepare task and network. Allocate space.
//
mlpbase.mlpcreatec0(nvars, nclasses, ref network);
mlpbase.mlpinitpreprocessor(ref network, ref xy, npoints);
mlpbase.mlpproperties(ref network, ref nin, ref nout, ref wcount);
for(i=0; i<=wcount-1; i++)
{
network.weights[i] = (2*AP.Math.RandomReal()-1)/nvars;
}
g = new double[wcount-1+1];
h = new double[wcount-1+1, wcount-1+1];
wbase = new double[wcount-1+1];
wdir = new double[wcount-1+1];
work = new double[wcount-1+1];
//
// First stage: optimize in gradient direction.
//
for(k=0; k<=wcount/3+10; k++)
{
//
// Calculate gradient in starting point
//
mlpbase.mlpgradnbatch(ref network, ref xy, npoints, ref e, ref g);
v = 0.0;
for(i_=0; i_<=wcount-1;i_++)
{
v += network.weights[i_]*network.weights[i_];
}
e = e+0.5*decay*v;
for(i_=0; i_<=wcount-1;i_++)
{
g[i_] = g[i_] + decay*network.weights[i_];
}
rep.ngrad = rep.ngrad+1;
//
// Setup optimization scheme
//
for(i_=0; i_<=wcount-1;i_++)
{
wdir[i_] = -g[i_];
}
v = 0.0;
for(i_=0; i_<=wcount-1;i_++)
{
v += wdir[i_]*wdir[i_];
}
wstep = Math.Sqrt(v);
v = 1/Math.Sqrt(v);
for(i_=0; i_<=wcount-1;i_++)
{
wdir[i_] = v*wdir[i_];
}
mcstage = 0;
mnlmcsrch(wcount, ref network.weights, ref e, ref g, ref wdir, ref wstep, ref mcinfo, ref mcnfev, ref work, ref mcstate, ref mcstage);
while( mcstage!=0 )
{
mlpbase.mlpgradnbatch(ref network, ref xy, npoints, ref e, ref g);
v = 0.0;
for(i_=0; i_<=wcount-1;i_++)
{
v += network.weights[i_]*network.weights[i_];
}
e = e+0.5*decay*v;
for(i_=0; i_<=wcount-1;i_++)
{
g[i_] = g[i_] + decay*network.weights[i_];
}
rep.ngrad = rep.ngrad+1;
mnlmcsrch(wcount, ref network.weights, ref e, ref g, ref wdir, ref wstep, ref mcinfo, ref mcnfev, ref work, ref mcstate, ref mcstage);
}
}
//
// Second stage: use Hessian when we are close to the minimum
//
while( true )
{
//
// Calculate and update E/G/H
//
mlpbase.mlphessiannbatch(ref network, ref xy, npoints, ref e, ref g, ref h);
v = 0.0;
for(i_=0; i_<=wcount-1;i_++)
{
v += network.weights[i_]*network.weights[i_];
}
e = e+0.5*decay*v;
for(i_=0; i_<=wcount-1;i_++)
{
g[i_] = g[i_] + decay*network.weights[i_];
}
for(k=0; k<=wcount-1; k++)
{
h[k,k] = h[k,k]+decay;
}
rep.nhess = rep.nhess+1;
//
// Select step direction
// NOTE: it is important to use lower-triangle Cholesky
// factorization since it is much faster than higher-triangle version.
//
spd = trfac.spdmatrixcholesky(ref h, wcount, false);
densesolver.spdmatrixcholeskysolve(ref h, wcount, false, ref g, ref solverinfo, ref solverrep, ref wdir);
spd = solverinfo>0;
if( spd )
{
//
// H is positive definite.
// Step in Newton direction.
//
for(i_=0; i_<=wcount-1;i_++)
{
wdir[i_] = -1*wdir[i_];
}
spd = true;
}
else
{
//
// H is indefinite.
// Step in gradient direction.
//
for(i_=0; i_<=wcount-1;i_++)
{
wdir[i_] = -g[i_];
}
spd = false;
}
//
// Optimize in WDir direction
//
v = 0.0;
for(i_=0; i_<=wcount-1;i_++)
{
v += wdir[i_]*wdir[i_];
}
wstep = Math.Sqrt(v);
v = 1/Math.Sqrt(v);
for(i_=0; i_<=wcount-1;i_++)
{
wdir[i_] = v*wdir[i_];
}
mcstage = 0;
mnlmcsrch(wcount, ref network.weights, ref e, ref g, ref wdir, ref wstep, ref mcinfo, ref mcnfev, ref work, ref mcstate, ref mcstage);
while( mcstage!=0 )
{
mlpbase.mlpgradnbatch(ref network, ref xy, npoints, ref e, ref g);
v = 0.0;
for(i_=0; i_<=wcount-1;i_++)
{
v += network.weights[i_]*network.weights[i_];
}
e = e+0.5*decay*v;
for(i_=0; i_<=wcount-1;i_++)
{
g[i_] = g[i_] + decay*network.weights[i_];
}
rep.ngrad = rep.ngrad+1;
mnlmcsrch(wcount, ref network.weights, ref e, ref g, ref wdir, ref wstep, ref mcinfo, ref mcnfev, ref work, ref mcstate, ref mcstage);
}
if( spd & (mcinfo==2 | mcinfo==4 | mcinfo==6) )
{
break;
}
}
//
// Convert from NN format to MNL format
//
i1_ = (0) - (offs);
for(i_=offs; i_<=offs+wcount-1;i_++)
{
lm.w[i_] = network.weights[i_+i1_];
}
for(k=0; k<=nvars-1; k++)
{
for(i=0; i<=nclasses-2; i++)
{
s = network.columnsigmas[k];
if( (double)(s)==(double)(0) )
{
s = 1;
}
j = offs+(nvars+1)*i;
v = lm.w[j+k];
lm.w[j+k] = v/s;
lm.w[j+nvars] = lm.w[j+nvars]+v*network.columnmeans[k]/s;
}
}
for(k=0; k<=nclasses-2; k++)
{
lm.w[offs+(nvars+1)*k+nvars] = -lm.w[offs+(nvars+1)*k+nvars];
}
}
public static bool testmlp(bool silent)
{
bool result = new bool();
bool waserrors = new bool();
int passcount = 0;
int maxn = 0;
int maxhid = 0;
int info = 0;
int nf = 0;
int nhid = 0;
int nl = 0;
int nhid1 = 0;
int nhid2 = 0;
int nkind = 0;
int i = 0;
int j = 0;
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
mlpbase.multilayerperceptron network2 = new mlpbase.multilayerperceptron();
mlptrain.mlpreport rep = new mlptrain.mlpreport();
mlptrain.mlpcvreport cvrep = new mlptrain.mlpcvreport();
int ncount = 0;
double[,] xy = new double[0,0];
double[,] valxy = new double[0,0];
int ssize = 0;
int valsize = 0;
bool allsame = new bool();
bool inferrors = new bool();
bool procerrors = new bool();
bool graderrors = new bool();
bool hesserrors = new bool();
bool trnerrors = new bool();
waserrors = false;
inferrors = false;
procerrors = false;
graderrors = false;
hesserrors = false;
trnerrors = false;
passcount = 10;
maxn = 4;
maxhid = 4;
//
// General multilayer network tests
//
for(nf=1; nf<=maxn; nf++)
{
for(nl=1; nl<=maxn; nl++)
{
for(nhid1=0; nhid1<=maxhid; nhid1++)
{
for(nhid2=0; nhid2<=0; nhid2++)
{
for(nkind=0; nkind<=3; nkind++)
{
//
// Skip meaningless parameters combinations
//
if( nkind==1 & nl<2 )
{
continue;
}
if( nhid1==0 & nhid2!=0 )
{
continue;
}
//
// Tests
//
testinformational(nkind, nf, nhid1, nhid2, nl, passcount, ref inferrors);
testprocessing(nkind, nf, nhid1, nhid2, nl, passcount, ref procerrors);
testgradient(nkind, nf, nhid1, nhid2, nl, passcount, ref graderrors);
testhessian(nkind, nf, nhid1, nhid2, nl, passcount, ref hesserrors);
}
}
}
}
}
//
// Test network training on simple XOR problem
//
xy = new double[3+1, 2+1];
xy[0,0] = -1;
xy[0,1] = -1;
xy[0,2] = -1;
xy[1,0] = +1;
xy[1,1] = -1;
xy[1,2] = +1;
xy[2,0] = -1;
xy[2,1] = +1;
xy[2,2] = +1;
xy[3,0] = +1;
xy[3,1] = +1;
xy[3,2] = -1;
mlpbase.mlpcreate1(2, 2, 1, ref network);
mlptrain.mlptrainlm(ref network, ref xy, 4, 0.001, 10, ref info, ref rep);
trnerrors = trnerrors | (double)(mlpbase.mlprmserror(ref network, ref xy, 4))>(double)(0.1);
//
// Test CV on random noisy problem
//
ncount = 100;
xy = new double[ncount-1+1, 1+1];
for(i=0; i<=ncount-1; i++)
{
xy[i,0] = 2*AP.Math.RandomReal()-1;
xy[i,1] = AP.Math.RandomInteger(4);
}
mlpbase.mlpcreatec0(1, 4, ref network);
mlptrain.mlpkfoldcvlm(ref network, ref xy, ncount, 0.001, 5, 10, ref info, ref rep, ref cvrep);
//
// Final report
//
waserrors = inferrors | procerrors | graderrors | hesserrors | trnerrors;
if( !silent )
{
System.Console.Write("MLP TEST");
System.Console.WriteLine();
System.Console.Write("INFORMATIONAL FUNCTIONS: ");
if( !inferrors )
{
System.Console.Write("OK");
System.Console.WriteLine();
}
else
{
System.Console.Write("FAILED");
System.Console.WriteLine();
}
System.Console.Write("BASIC PROCESSING: ");
if( !procerrors )
{
System.Console.Write("OK");
System.Console.WriteLine();
}
else
{
System.Console.Write("FAILED");
System.Console.WriteLine();
}
System.Console.Write("GRADIENT CALCULATION: ");
if( !graderrors )
{
System.Console.Write("OK");
System.Console.WriteLine();
}
else
{
System.Console.Write("FAILED");
System.Console.WriteLine();
}
System.Console.Write("HESSIAN CALCULATION: ");
if( !hesserrors )
{
System.Console.Write("OK");
System.Console.WriteLine();
}
else
{
System.Console.Write("FAILED");
System.Console.WriteLine();
}
System.Console.Write("TRAINING: ");
if( !trnerrors )
{
System.Console.Write("OK");
System.Console.WriteLine();
}
else
{
System.Console.Write("FAILED");
System.Console.WriteLine();
}
if( waserrors )
{
System.Console.Write("TEST SUMMARY: FAILED");
System.Console.WriteLine();
}
else
{
System.Console.Write("TEST SUMMARY: PASSED");
System.Console.WriteLine();
}
System.Console.WriteLine();
System.Console.WriteLine();
}
result = !waserrors;
return result;
}
/*************************************************************************
Gradient functions test
*************************************************************************/
private static void testgradient(int nkind,
int nin,
int nhid1,
int nhid2,
int nout,
int passcount,
ref bool err)
{
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
mlpbase.multilayerperceptron network2 = new mlpbase.multilayerperceptron();
int n1 = 0;
int n2 = 0;
int wcount = 0;
bool zeronet = new bool();
double h = 0;
double etol = 0;
double a1 = 0;
double a2 = 0;
int pass = 0;
int i = 0;
int j = 0;
int k = 0;
bool allsame = new bool();
int ilen = 0;
int rlen = 0;
int ssize = 0;
double[,] xy = new double[0,0];
double[] grad1 = new double[0];
double[] grad2 = new double[0];
double[] x = new double[0];
double[] y = new double[0];
double[] x1 = new double[0];
double[] x2 = new double[0];
double[] y1 = new double[0];
double[] y2 = new double[0];
int[] ia = new int[0];
double[] ra = new double[0];
double v = 0;
double e = 0;
double e1 = 0;
double e2 = 0;
double v1 = 0;
double v2 = 0;
double v3 = 0;
double v4 = 0;
double wprev = 0;
int i_ = 0;
int i1_ = 0;
System.Diagnostics.Debug.Assert(passcount>=2, "PassCount<2!");
a1 = 0;
a2 = 0;
if( nkind==2 )
{
a1 = 1000*AP.Math.RandomReal()-500;
a2 = 2*AP.Math.RandomReal()-1;
}
if( nkind==3 )
{
a1 = 1000*AP.Math.RandomReal()-500;
a2 = a1+(2*AP.Math.RandomInteger(2)-1)*(0.1+0.9*AP.Math.RandomReal());
}
createnetwork(ref network, nkind, a1, a2, nin, nhid1, nhid2, nout);
mlpbase.mlpproperties(ref network, ref n1, ref n2, ref wcount);
h = 0.0001;
etol = 0.01;
//
// Initialize
//
x = new double[nin-1+1];
x1 = new double[nin-1+1];
x2 = new double[nin-1+1];
y = new double[nout-1+1];
y1 = new double[nout-1+1];
y2 = new double[nout-1+1];
grad1 = new double[wcount-1+1];
grad2 = new double[wcount-1+1];
//
// Process
//
for(pass=1; pass<=passcount; pass++)
{
mlpbase.mlprandomizefull(ref network);
//
// Test error/gradient calculation (least squares)
//
xy = new double[0+1, nin+nout-1+1];
for(i=0; i<=nin-1; i++)
{
x[i] = 4*AP.Math.RandomReal()-2;
}
for(i_=0; i_<=nin-1;i_++)
{
xy[0,i_] = x[i_];
}
if( mlpbase.mlpissoftmax(ref network) )
{
for(i=0; i<=nout-1; i++)
{
y[i] = 0;
}
xy[0,nin] = AP.Math.RandomInteger(nout);
y[(int)Math.Round(xy[0,nin])] = 1;
}
else
{
for(i=0; i<=nout-1; i++)
{
y[i] = 4*AP.Math.RandomReal()-2;
}
i1_ = (0) - (nin);
for(i_=nin; i_<=nin+nout-1;i_++)
{
xy[0,i_] = y[i_+i1_];
}
}
mlpbase.mlpgrad(ref network, ref x, ref y, ref e, ref grad2);
mlpbase.mlpprocess(ref network, ref x, ref y2);
for(i_=0; i_<=nout-1;i_++)
{
y2[i_] = y2[i_] - y[i_];
}
v = 0.0;
for(i_=0; i_<=nout-1;i_++)
{
v += y2[i_]*y2[i_];
}
v = v/2;
err = err | (double)(Math.Abs((v-e)/v))>(double)(etol);
err = err | (double)(Math.Abs((mlpbase.mlperror(ref network, ref xy, 1)-v)/v))>(double)(etol);
for(i=0; i<=wcount-1; i++)
{
wprev = network.weights[i];
network.weights[i] = wprev-2*h;
mlpbase.mlpprocess(ref network, ref x, ref y1);
for(i_=0; i_<=nout-1;i_++)
{
y1[i_] = y1[i_] - y[i_];
}
v1 = 0.0;
for(i_=0; i_<=nout-1;i_++)
{
v1 += y1[i_]*y1[i_];
}
v1 = v1/2;
network.weights[i] = wprev-h;
mlpbase.mlpprocess(ref network, ref x, ref y1);
for(i_=0; i_<=nout-1;i_++)
{
y1[i_] = y1[i_] - y[i_];
}
v2 = 0.0;
for(i_=0; i_<=nout-1;i_++)
{
v2 += y1[i_]*y1[i_];
}
v2 = v2/2;
network.weights[i] = wprev+h;
mlpbase.mlpprocess(ref network, ref x, ref y1);
for(i_=0; i_<=nout-1;i_++)
{
y1[i_] = y1[i_] - y[i_];
}
v3 = 0.0;
for(i_=0; i_<=nout-1;i_++)
{
v3 += y1[i_]*y1[i_];
}
v3 = v3/2;
network.weights[i] = wprev+2*h;
mlpbase.mlpprocess(ref network, ref x, ref y1);
for(i_=0; i_<=nout-1;i_++)
{
y1[i_] = y1[i_] - y[i_];
}
v4 = 0.0;
for(i_=0; i_<=nout-1;i_++)
{
v4 += y1[i_]*y1[i_];
}
v4 = v4/2;
network.weights[i] = wprev;
grad1[i] = (v1-8*v2+8*v3-v4)/(12*h);
if( (double)(Math.Abs(grad1[i]))>(double)(1.0E-3) )
{
err = err | (double)(Math.Abs((grad2[i]-grad1[i])/grad1[i]))>(double)(etol);
}
else
{
err = err | (double)(Math.Abs(grad2[i]-grad1[i]))>(double)(etol);
}
}
//
// Test error/gradient calculation (natural).
// Testing on non-random structure networks
// (because NKind is representative only in that case).
//
xy = new double[0+1, nin+nout-1+1];
for(i=0; i<=nin-1; i++)
{
x[i] = 4*AP.Math.RandomReal()-2;
}
for(i_=0; i_<=nin-1;i_++)
{
xy[0,i_] = x[i_];
}
if( mlpbase.mlpissoftmax(ref network) )
{
for(i=0; i<=nout-1; i++)
{
y[i] = 0;
}
xy[0,nin] = AP.Math.RandomInteger(nout);
y[(int)Math.Round(xy[0,nin])] = 1;
}
else
{
for(i=0; i<=nout-1; i++)
{
y[i] = 4*AP.Math.RandomReal()-2;
}
i1_ = (0) - (nin);
for(i_=nin; i_<=nin+nout-1;i_++)
{
xy[0,i_] = y[i_+i1_];
}
}
mlpbase.mlpgradn(ref network, ref x, ref y, ref e, ref grad2);
mlpbase.mlpprocess(ref network, ref x, ref y2);
v = 0;
if( nkind!=1 )
{
for(i=0; i<=nout-1; i++)
{
v = v+0.5*AP.Math.Sqr(y2[i]-y[i]);
}
}
else
{
for(i=0; i<=nout-1; i++)
{
if( (double)(y[i])!=(double)(0) )
{
if( (double)(y2[i])==(double)(0) )
{
v = v+y[i]*Math.Log(AP.Math.MaxRealNumber);
}
else
{
v = v+y[i]*Math.Log(y[i]/y2[i]);
}
}
}
}
err = err | (double)(Math.Abs((v-e)/v))>(double)(etol);
err = err | (double)(Math.Abs((mlpbase.mlperrorn(ref network, ref xy, 1)-v)/v))>(double)(etol);
for(i=0; i<=wcount-1; i++)
{
wprev = network.weights[i];
network.weights[i] = wprev+h;
mlpbase.mlpprocess(ref network, ref x, ref y2);
network.weights[i] = wprev-h;
mlpbase.mlpprocess(ref network, ref x, ref y1);
network.weights[i] = wprev;
v = 0;
if( nkind!=1 )
{
for(j=0; j<=nout-1; j++)
{
v = v+0.5*(AP.Math.Sqr(y2[j]-y[j])-AP.Math.Sqr(y1[j]-y[j]))/(2*h);
}
}
else
{
for(j=0; j<=nout-1; j++)
{
if( (double)(y[j])!=(double)(0) )
{
if( (double)(y2[j])==(double)(0) )
{
v = v+y[j]*Math.Log(AP.Math.MaxRealNumber);
}
else
{
v = v+y[j]*Math.Log(y[j]/y2[j]);
}
if( (double)(y1[j])==(double)(0) )
{
v = v-y[j]*Math.Log(AP.Math.MaxRealNumber);
}
else
{
v = v-y[j]*Math.Log(y[j]/y1[j]);
}
}
}
v = v/(2*h);
}
grad1[i] = v;
if( (double)(Math.Abs(grad1[i]))>(double)(1.0E-3) )
{
err = err | (double)(Math.Abs((grad2[i]-grad1[i])/grad1[i]))>(double)(etol);
}
else
{
err = err | (double)(Math.Abs(grad2[i]-grad1[i]))>(double)(etol);
}
}
//
// Test gradient calculation: batch (least squares)
//
ssize = 1+AP.Math.RandomInteger(10);
xy = new double[ssize-1+1, nin+nout-1+1];
for(i=0; i<=wcount-1; i++)
{
grad1[i] = 0;
}
e1 = 0;
for(i=0; i<=ssize-1; i++)
{
for(j=0; j<=nin-1; j++)
{
x1[j] = 4*AP.Math.RandomReal()-2;
}
for(i_=0; i_<=nin-1;i_++)
{
xy[i,i_] = x1[i_];
}
if( mlpbase.mlpissoftmax(ref network) )
{
for(j=0; j<=nout-1; j++)
{
y1[j] = 0;
}
xy[i,nin] = AP.Math.RandomInteger(nout);
y1[(int)Math.Round(xy[i,nin])] = 1;
}
else
{
for(j=0; j<=nout-1; j++)
{
y1[j] = 4*AP.Math.RandomReal()-2;
}
i1_ = (0) - (nin);
for(i_=nin; i_<=nin+nout-1;i_++)
{
xy[i,i_] = y1[i_+i1_];
}
}
mlpbase.mlpgrad(ref network, ref x1, ref y1, ref v, ref grad2);
e1 = e1+v;
for(i_=0; i_<=wcount-1;i_++)
{
grad1[i_] = grad1[i_] + grad2[i_];
}
}
mlpbase.mlpgradbatch(ref network, ref xy, ssize, ref e2, ref grad2);
err = err | (double)(Math.Abs(e1-e2)/e1)>(double)(0.01);
for(i=0; i<=wcount-1; i++)
{
if( (double)(grad1[i])!=(double)(0) )
{
err = err | (double)(Math.Abs((grad2[i]-grad1[i])/grad1[i]))>(double)(etol);
}
else
{
err = err | (double)(grad2[i])!=(double)(grad1[i]);
}
}
//
// Test gradient calculation: batch (natural error func)
//
ssize = 1+AP.Math.RandomInteger(10);
xy = new double[ssize-1+1, nin+nout-1+1];
for(i=0; i<=wcount-1; i++)
{
grad1[i] = 0;
}
e1 = 0;
for(i=0; i<=ssize-1; i++)
{
for(j=0; j<=nin-1; j++)
{
x1[j] = 4*AP.Math.RandomReal()-2;
}
for(i_=0; i_<=nin-1;i_++)
{
xy[i,i_] = x1[i_];
}
if( mlpbase.mlpissoftmax(ref network) )
{
for(j=0; j<=nout-1; j++)
{
y1[j] = 0;
}
xy[i,nin] = AP.Math.RandomInteger(nout);
y1[(int)Math.Round(xy[i,nin])] = 1;
}
else
{
for(j=0; j<=nout-1; j++)
{
y1[j] = 4*AP.Math.RandomReal()-2;
}
i1_ = (0) - (nin);
for(i_=nin; i_<=nin+nout-1;i_++)
{
xy[i,i_] = y1[i_+i1_];
}
}
mlpbase.mlpgradn(ref network, ref x1, ref y1, ref v, ref grad2);
e1 = e1+v;
for(i_=0; i_<=wcount-1;i_++)
{
grad1[i_] = grad1[i_] + grad2[i_];
}
}
mlpbase.mlpgradnbatch(ref network, ref xy, ssize, ref e2, ref grad2);
err = err | (double)(Math.Abs(e1-e2)/e1)>(double)(etol);
for(i=0; i<=wcount-1; i++)
{
if( (double)(grad1[i])!=(double)(0) )
{
err = err | (double)(Math.Abs((grad2[i]-grad1[i])/grad1[i]))>(double)(etol);
}
else
{
err = err | (double)(grad2[i])!=(double)(grad1[i]);
}
}
}
}
/*************************************************************************
Processing functions test
*************************************************************************/
private static void testprocessing(int nkind,
int nin,
int nhid1,
int nhid2,
int nout,
int passcount,
ref bool err)
{
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
mlpbase.multilayerperceptron network2 = new mlpbase.multilayerperceptron();
int n1 = 0;
int n2 = 0;
int wcount = 0;
bool zeronet = new bool();
double a1 = 0;
double a2 = 0;
int pass = 0;
int i = 0;
bool allsame = new bool();
int rlen = 0;
double[] x1 = new double[0];
double[] x2 = new double[0];
double[] y1 = new double[0];
double[] y2 = new double[0];
double[] ra = new double[0];
double[] ra2 = new double[0];
double v = 0;
int i_ = 0;
System.Diagnostics.Debug.Assert(passcount>=2, "PassCount<2!");
//
// Prepare network
//
a1 = 0;
a2 = 0;
if( nkind==2 )
{
a1 = 1000*AP.Math.RandomReal()-500;
a2 = 2*AP.Math.RandomReal()-1;
}
if( nkind==3 )
{
a1 = 1000*AP.Math.RandomReal()-500;
a2 = a1+(2*AP.Math.RandomInteger(2)-1)*(0.1+0.9*AP.Math.RandomReal());
}
createnetwork(ref network, nkind, a1, a2, nin, nhid1, nhid2, nout);
mlpbase.mlpproperties(ref network, ref n1, ref n2, ref wcount);
//
// Initialize arrays
//
x1 = new double[nin-1+1];
x2 = new double[nin-1+1];
y1 = new double[nout-1+1];
y2 = new double[nout-1+1];
//
// Main cycle
//
for(pass=1; pass<=passcount; pass++)
{
//
// Last run is made on zero network
//
mlpbase.mlprandomizefull(ref network);
zeronet = false;
if( pass==passcount )
{
for(i_=0; i_<=wcount-1;i_++)
{
network.weights[i_] = 0*network.weights[i_];
}
zeronet = true;
}
//
// Same inputs leads to same outputs
//
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
x2[i] = x1[i];
}
for(i=0; i<=nout-1; i++)
{
y1[i] = 2*AP.Math.RandomReal()-1;
y2[i] = 2*AP.Math.RandomReal()-1;
}
mlpbase.mlpprocess(ref network, ref x1, ref y1);
mlpbase.mlpprocess(ref network, ref x2, ref y2);
allsame = true;
for(i=0; i<=nout-1; i++)
{
allsame = allsame & (double)(y1[i])==(double)(y2[i]);
}
err = err | !allsame;
//
// Same inputs on original network leads to same outputs
// on copy created using MLPCopy
//
unsetnetwork(ref network2);
mlpbase.mlpcopy(ref network, ref network2);
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
x2[i] = x1[i];
}
for(i=0; i<=nout-1; i++)
{
y1[i] = 2*AP.Math.RandomReal()-1;
y2[i] = 2*AP.Math.RandomReal()-1;
}
mlpbase.mlpprocess(ref network, ref x1, ref y1);
mlpbase.mlpprocess(ref network2, ref x2, ref y2);
allsame = true;
for(i=0; i<=nout-1; i++)
{
allsame = allsame & (double)(y1[i])==(double)(y2[i]);
}
err = err | !allsame;
//
// Same inputs on original network leads to same outputs
// on copy created using MLPSerialize
//
unsetnetwork(ref network2);
mlpbase.mlpserialize(ref network, ref ra, ref rlen);
ra2 = new double[rlen-1+1];
for(i=0; i<=rlen-1; i++)
{
ra2[i] = ra[i];
}
mlpbase.mlpunserialize(ref ra2, ref network2);
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
x2[i] = x1[i];
}
for(i=0; i<=nout-1; i++)
{
y1[i] = 2*AP.Math.RandomReal()-1;
y2[i] = 2*AP.Math.RandomReal()-1;
}
mlpbase.mlpprocess(ref network, ref x1, ref y1);
mlpbase.mlpprocess(ref network2, ref x2, ref y2);
allsame = true;
for(i=0; i<=nout-1; i++)
{
allsame = allsame & (double)(y1[i])==(double)(y2[i]);
}
err = err | !allsame;
//
// Different inputs leads to different outputs (non-zero network)
//
if( !zeronet )
{
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
x2[i] = 2*AP.Math.RandomReal()-1;
}
for(i=0; i<=nout-1; i++)
{
y1[i] = 2*AP.Math.RandomReal()-1;
y2[i] = y1[i];
}
mlpbase.mlpprocess(ref network, ref x1, ref y1);
mlpbase.mlpprocess(ref network, ref x2, ref y2);
allsame = true;
for(i=0; i<=nout-1; i++)
{
allsame = allsame & (double)(y1[i])==(double)(y2[i]);
}
err = err | allsame;
}
//
// Randomization changes outputs (when inputs are unchanged, non-zero network)
//
if( !zeronet )
{
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
x2[i] = 2*AP.Math.RandomReal()-1;
}
for(i=0; i<=nout-1; i++)
{
y1[i] = 2*AP.Math.RandomReal()-1;
y2[i] = y1[i];
}
mlpbase.mlpcopy(ref network, ref network2);
mlpbase.mlprandomize(ref network2);
mlpbase.mlpprocess(ref network, ref x1, ref y1);
mlpbase.mlpprocess(ref network2, ref x1, ref y2);
allsame = true;
for(i=0; i<=nout-1; i++)
{
allsame = allsame & (double)(y1[i])==(double)(y2[i]);
}
err = err | allsame;
}
//
// Full randomization changes outputs (when inputs are unchanged, non-zero network)
//
if( !zeronet )
{
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
x2[i] = 2*AP.Math.RandomReal()-1;
}
for(i=0; i<=nout-1; i++)
{
y1[i] = 2*AP.Math.RandomReal()-1;
y2[i] = y1[i];
}
mlpbase.mlpcopy(ref network, ref network2);
mlpbase.mlprandomizefull(ref network2);
mlpbase.mlpprocess(ref network, ref x1, ref y1);
mlpbase.mlpprocess(ref network2, ref x1, ref y2);
allsame = true;
for(i=0; i<=nout-1; i++)
{
allsame = allsame & (double)(y1[i])==(double)(y2[i]);
}
err = err | allsame;
}
//
// Normalization properties
//
if( nkind==1 )
{
//
// Classifier network outputs are normalized
//
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
}
mlpbase.mlpprocess(ref network, ref x1, ref y1);
v = 0;
for(i=0; i<=nout-1; i++)
{
v = v+y1[i];
err = err | (double)(y1[i])<(double)(0);
}
err = err | (double)(Math.Abs(v-1))>(double)(1000*AP.Math.MachineEpsilon);
}
if( nkind==2 )
{
//
// B-type network outputs are bounded from above/below
//
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
}
mlpbase.mlpprocess(ref network, ref x1, ref y1);
for(i=0; i<=nout-1; i++)
{
if( (double)(a2)>=(double)(0) )
{
err = err | (double)(y1[i])<(double)(a1);
}
else
{
err = err | (double)(y1[i])>(double)(a1);
}
}
}
if( nkind==3 )
{
//
// R-type network outputs are within [A1,A2] (or [A2,A1])
//
for(i=0; i<=nin-1; i++)
{
x1[i] = 2*AP.Math.RandomReal()-1;
}
mlpbase.mlpprocess(ref network, ref x1, ref y1);
for(i=0; i<=nout-1; i++)
{
err = err | (double)(y1[i])<(double)(Math.Min(a1, a2)) | (double)(y1[i])>(double)(Math.Max(a1, a2));
}
}
}
}
/*************************************************************************
Iformational functions test
*************************************************************************/
private static void testinformational(int nkind,
int nin,
int nhid1,
int nhid2,
int nout,
int passcount,
ref bool err)
{
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
int n1 = 0;
int n2 = 0;
int wcount = 0;
createnetwork(ref network, nkind, 0.0, 0.0, nin, nhid1, nhid2, nout);
mlpbase.mlpproperties(ref network, ref n1, ref n2, ref wcount);
err = err | n1!=nin | n2!=nout | wcount<=0;
}
/*************************************************************************
Hessian functions test
*************************************************************************/
private static void testhessian(int nkind,
int nin,
int nhid1,
int nhid2,
int nout,
int passcount,
ref bool err)
{
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
mlpbase.multilayerperceptron network2 = new mlpbase.multilayerperceptron();
int hkind = 0;
int n1 = 0;
int n2 = 0;
int wcount = 0;
bool zeronet = new bool();
double h = 0;
double etol = 0;
int pass = 0;
int i = 0;
int j = 0;
bool allsame = new bool();
int ilen = 0;
int rlen = 0;
int ssize = 0;
double a1 = 0;
double a2 = 0;
double[,] xy = new double[0,0];
double[,] h1 = new double[0,0];
double[,] h2 = new double[0,0];
double[] grad1 = new double[0];
double[] grad2 = new double[0];
double[] grad3 = new double[0];
double[] x = new double[0];
double[] y = new double[0];
double[] x1 = new double[0];
double[] x2 = new double[0];
double[] y1 = new double[0];
double[] y2 = new double[0];
int[] ia = new int[0];
double[] ra = new double[0];
double v = 0;
double e = 0;
double e1 = 0;
double e2 = 0;
double v1 = 0;
double v2 = 0;
double v3 = 0;
double v4 = 0;
double wprev = 0;
int i_ = 0;
int i1_ = 0;
System.Diagnostics.Debug.Assert(passcount>=2, "PassCount<2!");
a1 = 0;
a2 = 0;
if( nkind==2 )
{
a1 = 1000*AP.Math.RandomReal()-500;
a2 = 2*AP.Math.RandomReal()-1;
}
if( nkind==3 )
{
a1 = 1000*AP.Math.RandomReal()-500;
a2 = a1+(2*AP.Math.RandomInteger(2)-1)*(0.1+0.9*AP.Math.RandomReal());
}
createnetwork(ref network, nkind, a1, a2, nin, nhid1, nhid2, nout);
mlpbase.mlpproperties(ref network, ref n1, ref n2, ref wcount);
h = 0.0001;
etol = 0.05;
//
// Initialize
//
x = new double[nin-1+1];
x1 = new double[nin-1+1];
x2 = new double[nin-1+1];
y = new double[nout-1+1];
y1 = new double[nout-1+1];
y2 = new double[nout-1+1];
grad1 = new double[wcount-1+1];
grad2 = new double[wcount-1+1];
grad3 = new double[wcount-1+1];
h1 = new double[wcount-1+1, wcount-1+1];
h2 = new double[wcount-1+1, wcount-1+1];
//
// Process
//
for(pass=1; pass<=passcount; pass++)
{
mlpbase.mlprandomizefull(ref network);
//
// Test hessian calculation .
// E1 contains total error (calculated using MLPGrad/MLPGradN)
// Grad1 contains total gradient (calculated using MLPGrad/MLPGradN)
// H1 contains Hessian calculated using differences of gradients
//
// E2, Grad2 and H2 contains corresponing values calculated using MLPHessianBatch/MLPHessianNBatch
//
for(hkind=0; hkind<=1; hkind++)
{
ssize = 1+AP.Math.RandomInteger(10);
xy = new double[ssize-1+1, nin+nout-1+1];
for(i=0; i<=wcount-1; i++)
{
grad1[i] = 0;
}
for(i=0; i<=wcount-1; i++)
{
for(j=0; j<=wcount-1; j++)
{
h1[i,j] = 0;
}
}
e1 = 0;
for(i=0; i<=ssize-1; i++)
{
//
// X, Y
//
for(j=0; j<=nin-1; j++)
{
x1[j] = 4*AP.Math.RandomReal()-2;
}
for(i_=0; i_<=nin-1;i_++)
{
xy[i,i_] = x1[i_];
}
if( mlpbase.mlpissoftmax(ref network) )
{
for(j=0; j<=nout-1; j++)
{
y1[j] = 0;
}
xy[i,nin] = AP.Math.RandomInteger(nout);
y1[(int)Math.Round(xy[i,nin])] = 1;
}
else
{
for(j=0; j<=nout-1; j++)
{
y1[j] = 4*AP.Math.RandomReal()-2;
}
i1_ = (0) - (nin);
for(i_=nin; i_<=nin+nout-1;i_++)
{
xy[i,i_] = y1[i_+i1_];
}
}
//
// E1, Grad1
//
if( hkind==0 )
{
mlpbase.mlpgrad(ref network, ref x1, ref y1, ref v, ref grad2);
}
else
{
mlpbase.mlpgradn(ref network, ref x1, ref y1, ref v, ref grad2);
}
e1 = e1+v;
for(i_=0; i_<=wcount-1;i_++)
{
grad1[i_] = grad1[i_] + grad2[i_];
}
//
// H1
//
for(j=0; j<=wcount-1; j++)
{
wprev = network.weights[j];
network.weights[j] = wprev-2*h;
if( hkind==0 )
{
mlpbase.mlpgrad(ref network, ref x1, ref y1, ref v, ref grad2);
}
else
{
mlpbase.mlpgradn(ref network, ref x1, ref y1, ref v, ref grad2);
}
network.weights[j] = wprev-h;
if( hkind==0 )
{
mlpbase.mlpgrad(ref network, ref x1, ref y1, ref v, ref grad3);
}
else
{
mlpbase.mlpgradn(ref network, ref x1, ref y1, ref v, ref grad3);
}
for(i_=0; i_<=wcount-1;i_++)
{
grad2[i_] = grad2[i_] - 8*grad3[i_];
}
network.weights[j] = wprev+h;
if( hkind==0 )
{
mlpbase.mlpgrad(ref network, ref x1, ref y1, ref v, ref grad3);
}
else
{
mlpbase.mlpgradn(ref network, ref x1, ref y1, ref v, ref grad3);
}
for(i_=0; i_<=wcount-1;i_++)
{
grad2[i_] = grad2[i_] + 8*grad3[i_];
}
network.weights[j] = wprev+2*h;
if( hkind==0 )
{
mlpbase.mlpgrad(ref network, ref x1, ref y1, ref v, ref grad3);
}
else
{
mlpbase.mlpgradn(ref network, ref x1, ref y1, ref v, ref grad3);
}
for(i_=0; i_<=wcount-1;i_++)
{
grad2[i_] = grad2[i_] - grad3[i_];
}
v = 1/(12*h);
for(i_=0; i_<=wcount-1;i_++)
{
h1[j,i_] = h1[j,i_] + v*grad2[i_];
}
network.weights[j] = wprev;
}
}
if( hkind==0 )
{
mlpbase.mlphessianbatch(ref network, ref xy, ssize, ref e2, ref grad2, ref h2);
}
else
{
mlpbase.mlphessiannbatch(ref network, ref xy, ssize, ref e2, ref grad2, ref h2);
}
err = err | (double)(Math.Abs(e1-e2)/e1)>(double)(etol);
for(i=0; i<=wcount-1; i++)
{
if( (double)(Math.Abs(grad1[i]))>(double)(1.0E-2) )
{
err = err | (double)(Math.Abs((grad2[i]-grad1[i])/grad1[i]))>(double)(etol);
}
else
{
err = err | (double)(Math.Abs(grad2[i]-grad1[i]))>(double)(etol);
}
}
for(i=0; i<=wcount-1; i++)
{
for(j=0; j<=wcount-1; j++)
{
if( (double)(Math.Abs(h1[i,j]))>(double)(5.0E-2) )
{
err = err | (double)(Math.Abs((h1[i,j]-h2[i,j])/h1[i,j]))>(double)(etol);
}
else
{
err = err | (double)(Math.Abs(h2[i,j]-h1[i,j]))>(double)(etol);
}
}
}
}
}
}
/*************************************************************************
Training neural networks ensemble using early stopping.
INPUT PARAMETERS:
Ensemble - model with initialized geometry
XY - training set
NPoints - training set size
Decay - weight decay coefficient, >=0.001
Restarts - restarts, >0.
OUTPUT PARAMETERS:
Ensemble - trained model
Info - return code:
* -2, if there is a point with class number
outside of [0..NClasses-1].
* -1, if incorrect parameters was passed
(NPoints<0, Restarts<1).
* 6, if task has been solved.
Rep - training report.
OOBErrors - out-of-bag generalization error estimate
-- ALGLIB --
Copyright 10.03.2009 by Bochkanov Sergey
*************************************************************************/
public static void mlpetraines(ref mlpensemble ensemble,
ref double[,] xy,
int npoints,
double decay,
int restarts,
ref int info,
ref mlptrain.mlpreport rep)
{
int i = 0;
int k = 0;
int ccount = 0;
int pcount = 0;
double[,] trnxy = new double[0,0];
double[,] valxy = new double[0,0];
int trnsize = 0;
int valsize = 0;
mlpbase.multilayerperceptron network = new mlpbase.multilayerperceptron();
int tmpinfo = 0;
mlptrain.mlpreport tmprep = new mlptrain.mlpreport();
int i_ = 0;
int i1_ = 0;
if( npoints<2 | restarts<1 | (double)(decay)<(double)(0) )
{
info = -1;
return;
}
if( ensemble.issoftmax )
{
for(i=0; i<=npoints-1; i++)
{
if( (int)Math.Round(xy[i,ensemble.nin])<0 | (int)Math.Round(xy[i,ensemble.nin])>=ensemble.nout )
{
info = -2;
return;
}
}
}
info = 6;
//
// allocate
//
if( ensemble.issoftmax )
{
ccount = ensemble.nin+1;
pcount = ensemble.nin;
}
else
{
ccount = ensemble.nin+ensemble.nout;
pcount = ensemble.nin+ensemble.nout;
}
trnxy = new double[npoints-1+1, ccount-1+1];
valxy = new double[npoints-1+1, ccount-1+1];
mlpbase.mlpunserialize(ref ensemble.serializedmlp, ref network);
rep.ngrad = 0;
rep.nhess = 0;
rep.ncholesky = 0;
//
// train networks
//
for(k=0; k<=ensemble.ensemblesize-1; k++)
{
//
// Split set
//
do
{
trnsize = 0;
valsize = 0;
for(i=0; i<=npoints-1; i++)
{
if( (double)(AP.Math.RandomReal())<(double)(0.66) )
{
//
// Assign sample to training set
//
for(i_=0; i_<=ccount-1;i_++)
{
trnxy[trnsize,i_] = xy[i,i_];
}
trnsize = trnsize+1;
}
else
{
//
// Assign sample to validation set
//
for(i_=0; i_<=ccount-1;i_++)
{
valxy[valsize,i_] = xy[i,i_];
}
valsize = valsize+1;
}
}
}
while( ! (trnsize!=0 & valsize!=0) );
//
// Train
//
mlptrain.mlptraines(ref network, ref trnxy, trnsize, ref valxy, valsize, decay, restarts, ref tmpinfo, ref tmprep);
if( tmpinfo<0 )
{
info = tmpinfo;
return;
}
//
// save results
//
i1_ = (0) - (k*ensemble.wcount);
for(i_=k*ensemble.wcount; i_<=(k+1)*ensemble.wcount-1;i_++)
{
ensemble.weights[i_] = network.weights[i_+i1_];
}
i1_ = (0) - (k*pcount);
for(i_=k*pcount; i_<=(k+1)*pcount-1;i_++)
{
ensemble.columnmeans[i_] = network.columnmeans[i_+i1_];
}
i1_ = (0) - (k*pcount);
for(i_=k*pcount; i_<=(k+1)*pcount-1;i_++)
{
ensemble.columnsigmas[i_] = network.columnsigmas[i_+i1_];
}
rep.ngrad = rep.ngrad+tmprep.ngrad;
rep.nhess = rep.nhess+tmprep.nhess;
rep.ncholesky = rep.ncholesky+tmprep.ncholesky;
}
}
