Exemple #1
0
void CMT::HistogramNonlinearity::initialize(
	const ArrayXXd& inputs,
	const ArrayXXd& outputs)
{
	if(inputs.rows() != outputs.rows() || inputs.cols() != outputs.cols())
		throw Exception("Inputs and outputs have to have same size.");

	mHistogram = vector<double>(mBinEdges.size() - 1);
	vector<int> counter(mBinEdges.size() - 1);

	for(int k = 0; k < mHistogram.size(); ++k) {
		mHistogram[k] = 0.;
		counter[k] = 0;
	}

	for(int i = 0; i < inputs.rows(); ++i)
		for(int j = 0; j < inputs.cols(); ++j) {
			// find bin
			int k = bin(inputs(i, j));

			// update histogram
			counter[k] += 1;
			mHistogram[k] += outputs(i, j);
		}

	for(int k = 0; k < mHistogram.size(); ++k)
		if(mHistogram[k] > 0.)
			// average output observed in bin k
			mHistogram[k] /= counter[k];
}
Exemple #2
0
ArrayXXd CMT::BlobNonlinearity::gradient(const ArrayXXd& inputs) const {
	if(inputs.rows() != 1)
		throw Exception("Data has to be stored in one row.");
	
	ArrayXXd diff = ArrayXXd::Zero(mNumComponents, inputs.cols());
	diff.rowwise() += inputs.row(0);
	diff.colwise() -= mMeans;

	ArrayXXd diffSq = diff.square();
	ArrayXd precisions = mLogPrecisions.exp();
	ArrayXd weights = mLogWeights.exp();

	ArrayXXd negEnergy = diffSq.colwise() * (-precisions / 2.);
	ArrayXXd negEnergyExp = negEnergy.exp();

	ArrayXXd gradient(3 * mNumComponents, inputs.cols());

	// gradient of mean
	gradient.topRows(mNumComponents) = (diff * negEnergyExp).colwise() * (weights * precisions);

	// gradient of log-precisions
	gradient.middleRows(mNumComponents, mNumComponents) = (diffSq / 2. * negEnergyExp).colwise() * (-weights * precisions);

	// gradient of log-weights
	gradient.bottomRows(mNumComponents) = negEnergyExp.colwise() * weights;

	return gradient;
}
Exemple #3
0
ArrayXXd CMT::HistogramNonlinearity::operator()(const ArrayXXd& inputs) const {
	ArrayXXd outputs(inputs.rows(), inputs.cols());

	for(int i = 0; i < inputs.rows(); ++i)
		for(int j = 0; j < inputs.cols(); ++j)
			outputs(i, j) = mHistogram[bin(inputs(i, j))] + mEpsilon;

	return outputs;
}
void NestedSampler::setPosteriorSample(ArrayXXd newPosteriorSample)
{
    Ndimensions = newPosteriorSample.rows();
    int Nsamples = newPosteriorSample.cols();
    posteriorSample.resize(Ndimensions, Nsamples);
    posteriorSample = newPosteriorSample;
}
Exemple #5
0
void CMT::WhiteningTransform::initialize(const ArrayXXd& input, int dimOut) {
	if(input.cols() < input.rows())
		throw Exception("Too few inputs to compute whitening transform."); 

	mMeanIn = input.rowwise().mean();

	// compute covariances
	MatrixXd covXX = covariance(input);

	// input whitening
	SelfAdjointEigenSolver<MatrixXd> eigenSolver;

	eigenSolver.compute(covXX);

	Array<double, 1, Dynamic> eigenvalues = eigenSolver.eigenvalues();
	MatrixXd eigenvectors = eigenSolver.eigenvectors();

	// don't whiten directions with near-zero variance
	for(int i = 0; i < eigenvalues.size(); ++i)
		if(eigenvalues[i] < 1e-7)
			eigenvalues[i] = 1.;

	mPreIn = (eigenvectors.array().rowwise() * eigenvalues.sqrt().cwiseInverse()).matrix()
		* eigenvectors.transpose();
	mPreInInv = (eigenvectors.array().rowwise() * eigenvalues.sqrt()).matrix()
		* eigenvectors.transpose();

	mMeanOut = VectorXd::Zero(dimOut);
	mPreOut = MatrixXd::Identity(dimOut, dimOut);
	mPreOutInv = MatrixXd::Identity(dimOut, dimOut);
	mPredictor = MatrixXd::Zero(dimOut, input.rows());
	mGradTransform = MatrixXd::Zero(dimOut, input.rows());
	mLogJacobian = 1.;
}
Exemple #6
0
ArrayXXd CMT::tanh(const ArrayXXd& arr) {
	ArrayXXd result(arr.rows(), arr.cols());

	#pragma omp parallel for
	for(int i = 0; i < arr.size(); ++i)
		result(i) = std::tanh(arr(i));

	return result;
}
Exemple #7
0
ArrayXXd CMT::BlobNonlinearity::operator()(const ArrayXXd& inputs) const {
	if(inputs.rows() != 1)
		throw Exception("Data has to be stored in one row.");

	ArrayXXd diff = ArrayXXd::Zero(mNumComponents, inputs.cols());
	diff.rowwise() += inputs.row(0);
	diff.colwise() -= mMeans;

	ArrayXXd negEnergy = diff.square().colwise() * (-mLogPrecisions.exp() / 2.);
	return (mLogWeights.exp().transpose().matrix() * negEnergy.exp().matrix()).array() + mEpsilon;
}
Exemple #8
0
ArrayXXd CMT::HistogramNonlinearity::gradient(const ArrayXXd& inputs) const {
	if(inputs.rows() != 1)
		throw Exception("Data has to be stored in one row.");

	ArrayXXd gradient = ArrayXXd::Zero(mHistogram.size(), inputs.cols());

	for(int i = 0; i < inputs.rows(); ++i)
		for(int j = 0; j < inputs.rows(); ++j)
			gradient(bin(inputs(i, j)), j) = 1;

	return gradient;
}
Exemple #9
0
ArrayXXd CMT::BlobNonlinearity::derivative(const ArrayXXd& inputs) const {
	if(inputs.rows() != 1)
		throw Exception("Data has to be stored in one row.");

	ArrayXXd diff = ArrayXXd::Zero(mNumComponents, inputs.cols());
	diff.rowwise() -= inputs.row(0);
	diff.colwise() += mMeans;

	ArrayXd precisions = mLogPrecisions.exp();

	ArrayXXd negEnergy = diff.square().colwise() * (-precisions / 2.);

	return (mLogWeights.exp() * precisions).transpose().matrix() * (diff * negEnergy.exp()).matrix();
}
Exemple #10
0
void
mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[]) {
    int N = mxGetScalar(prhs[0]);
    double d = mxGetScalar(prhs[1]);
    double h = mxGetScalar(prhs[2]);
    int Njacv = mxGetScalar(prhs[3]);
    double b = mxGetScalar(prhs[4]);
    double c = mxGetScalar(prhs[5]);
    double dr = mxGetScalar(prhs[6]);
    double di = mxGetScalar(prhs[7]);
    int threadNum = mxGetScalar(prhs[8]);

    double *a0 = mxGetPr(prhs[9]);
    double *v = mxGetPr(prhs[10]);
    double th = mxGetScalar(prhs[11]);
    double phi = mxGetScalar(prhs[12]);
    int nstp = mxGetScalar(prhs[13]);
    // mwSize isJ = mxGetScalar(prhs[14]);

    ArrayXXd av = gintgv(N, d, h, Njacv, b, c, dr, di, threadNum, a0, v, th, phi, nstp);
    plhs[0] = mxCreateDoubleMatrix(av.rows(), av.cols(), mxREAL);
    memcpy(mxGetPr(plhs[0]), av.data(), av.cols()*av.rows()*sizeof(double));
}
Exemple #11
0
ArrayXXi CMT::sampleBinomial(const ArrayXXi& n, const ArrayXXd& p) {
	if(n.rows() != p.rows() || n.cols() != p.cols())
		throw Exception("n and p must be of the same size.");

	ArrayXXi samples = ArrayXXi::Zero(n.rows(), n.cols());

	#pragma omp parallel for
	for(int i = 0; i < samples.size(); ++i) {
		// very naive algorithm for generating binomial samples
		for(int k = 0; k < n(i); ++k)
			if(rand() / static_cast<double>(RAND_MAX) < p(i))
				samples(i) += 1; 
	}

	return samples;
}
Exemple #12
0
/**
 * Algorithm due to Knuth, 1969.
 */
ArrayXXi CMT::samplePoisson(const ArrayXXd& lambda) {
	ArrayXXi samples(lambda.rows(), lambda.cols());
	ArrayXXd threshold = (-lambda).exp();

	#pragma omp parallel for
	for(int i = 0; i < samples.size(); ++i) {
		double p = rand() / static_cast<double>(RAND_MAX);
		int k = 0;

		while(p > threshold(i)) {
			k += 1;
			p *= rand() / static_cast<double>(RAND_MAX);
		}

		samples(i) = k;
	}

	return samples;
}
Exemple #13
0
pair<pair<ArrayXXd, ArrayXXd>, Array<double, 1, Dynamic> > CMT::STM::computeDataGradient(
	const MatrixXd& input,
	const MatrixXd& output) const
{
	// make sure nonlinearity is differentiable
	DifferentiableNonlinearity* nonlinearity =
		dynamic_cast<DifferentiableNonlinearity*>(mNonlinearity);
	if(!nonlinearity)
		throw Exception("Nonlinearity has to be differentiable.");

	if(input.rows() != dimIn())
		throw Exception("Input has wrong dimensionality.");
	if(output.rows() != 1)
		throw Exception("Output has wrong dimensionality.");
	if(input.cols() != output.cols())
		throw Exception("Number of inputs and outputs should be the same.");

	if(dimInNonlinear() && !dimInLinear()) {
		Array<double, 1, Dynamic> responses;

		ArrayXXd jointEnergy;

		if(numFeatures() > 0)
			jointEnergy = mWeights * (mFeatures.transpose() * input).array().square().matrix()
				+ mPredictors * input;
		else
			jointEnergy = mPredictors * input;
		jointEnergy.colwise() += mBiases.array();
		jointEnergy *= mSharpness;

		responses = logSumExp(jointEnergy);

		// posterior over components for each input
		MatrixXd posterior = (jointEnergy.rowwise() - responses).array().exp();

		responses /= mSharpness;

		Array<double, 1, Dynamic> tmp0 = (*mNonlinearity)(responses);
		Array<double, 1, Dynamic> tmp1 = -mDistribution->gradient(output, tmp0);
		Array<double, 1, Dynamic> tmp2 = nonlinearity->derivative(responses);

		ArrayXXd avgPredictor = mPredictors.transpose() * posterior;

		ArrayXXd tmp3;
		if(numFeatures() > 0) {
			ArrayXXd avgWeights = (2. * mWeights).transpose() * posterior;
			tmp3 = mFeatures * (avgWeights * (mFeatures.transpose() * input).array()).matrix();
		} else {
			tmp3 = ArrayXXd::Zero(avgPredictor.rows(), avgPredictor.cols());
		}

		return make_pair(
			make_pair(
				(tmp3 + avgPredictor).rowwise() * (tmp1 * tmp2),
				ArrayXXd::Zero(output.rows(), output.cols())),
			mDistribution->logLikelihood(output, tmp0));

	} else if(dimInNonlinear() && dimInLinear()) {
		// split inputs into linear and nonlinear components
		MatrixXd inputNonlinear = input.topRows(dimInNonlinear());
		MatrixXd inputLinear = input.bottomRows(dimInLinear());

		Array<double, 1, Dynamic> responses;

		ArrayXXd jointEnergy;

		if(numFeatures() > 0)
			jointEnergy = mWeights * (mFeatures.transpose() * inputNonlinear).array().square().matrix()
				+ mPredictors * input;
		else
			jointEnergy = mPredictors * inputNonlinear;
		jointEnergy.colwise() += mBiases.array();
		jointEnergy *= mSharpness;

		responses = logSumExp(jointEnergy);

		// posterior over components for each input
		MatrixXd posterior = (jointEnergy.rowwise() - responses).array().exp();

		responses /= mSharpness;
		responses += (mLinearPredictor.transpose() * inputLinear).array();

		Array<double, 1, Dynamic> tmp0 = (*mNonlinearity)(responses);
		Array<double, 1, Dynamic> tmp1 = -mDistribution->gradient(output, tmp0);
		Array<double, 1, Dynamic> tmp2 = nonlinearity->derivative(responses);

		ArrayXXd avgPredictor = mPredictors.transpose() * posterior;

		ArrayXXd tmp3;
		if(numFeatures() > 0) {
			ArrayXXd avgWeights = (2. * mWeights).transpose() * posterior;
			tmp3 = mFeatures * (avgWeights * (mFeatures.transpose() * inputNonlinear).array()).matrix();
		} else {
			tmp3 = ArrayXXd::Zero(avgPredictor.rows(), avgPredictor.cols());
		}

		// concatenate gradients of nonlinear and linear component
		ArrayXXd inputGradient(dimIn(), input.cols());
		inputGradient << 
			(tmp3 + avgPredictor).rowwise() * (tmp1 * tmp2),
			mLinearPredictor * (tmp1 * tmp2).matrix();

		return make_pair(
			make_pair(
				inputGradient,
				ArrayXXd::Zero(output.rows(), output.cols())),
			mDistribution->logLikelihood(output, tmp0));

	} else if(dimInLinear()) {
		double avgBias = logSumExp(mSharpness * mBiases)(0, 0) / mSharpness;
		Array<double, 1, Dynamic> responses = (mLinearPredictor.transpose() * input).array() + avgBias;

		Array<double, 1, Dynamic> tmp0 = (*mNonlinearity)(responses);
		Array<double, 1, Dynamic> tmp1 = -mDistribution->gradient(output, tmp0);
		Array<double, 1, Dynamic> tmp2 = nonlinearity->derivative(responses);

		return make_pair(
			make_pair(
				mLinearPredictor * (tmp1 * tmp2).matrix(),
				ArrayXXd::Zero(output.rows(), output.cols())),
			mDistribution->logLikelihood(output, tmp0));
	}

	return make_pair(
		make_pair(
			ArrayXXd::Zero(input.rows(), input.cols()),
			ArrayXXd::Zero(output.rows(), output.cols())),
		logLikelihood(input, output));
}