稀疏表示（SR）工具箱

应用背景这个工具箱包括机器学习方法：基于稀疏编码的分类，基于字典的降维子字典学习，学习模型，线性回归和分类（LRC）。核l_1正则或（和）非负约束稀疏编码和字典学习模型在这个工具箱实现。 ；关键技术活动集，内点，近端，和分解方法来优化这些模型。目前的版本是1.9（2015年3月2日）。这个工具箱是免费的学术用途。 ；

New folder
bootstrapnnlsClassifier.m
changeClassLabels01.m
classification.m
classificationPredict.m
classificationTrain.m
computeKernelMatrix.m
computeMetaSample.m
computeSparsity.m
cvExperiment.m
downsample.m
dynamicSystems_kernel.m
dynamicSystems_kernel2.m
EQP.m
estimatePQRS.m
euclidean.m
example.m
exampleClassification.m
exampleConstrainedNNQP.m
exampleDicLearn.m
exampleFeatExtr.m
exampleKSRDL.m
exampleKSRSC.m
examplel1QPSMO.m
exampleLRC.m
exampleOptSC.m
examplePlotBars.m
exampleUnboundedQPFeb212012.m
exampleUSR.m
exampleVSMF.m
featSel.m
featureExtractionTrain.m
featureExtrationTest.m
findViolateXl1QPSMO.m
FriedmanTest.m
genCode.m
geometricMean.m
getBestScores.m
getLambda.m
getRank.m
gridSearch.m
gridSearchUniverse.m
initializel1QPSMO.m
initializeNNQPSMO.m
innerProduct.m
invsvd.m
iszero.m
kernelLinear.m
kernelPoly.m
kernelRBF.m
kernelseminmfruletest.m
kernelSigmoid.m
kfcnnls.m
khdlmClassifier.m
khdlmPredict.m
khdlmTrain.m
knnrule.m
KSRDL.m
KSRDLDR.m
KSRSC.m
KSRSCClassifier.m
l1LSKernelBatch.m
l1NNLSKernel.m
l1NNLSKernelBatch.m
l1NNLSKernelBatchDL.m
l1NNQPActiveSet.m
l1NNQPActiveSetMultiTemp.m
l1QPActiveSet.m
l1QPIP.m
l1QPIPMulti.m
l1QPMultiTemp.m
l1QPProximal.m
l1QPProximalMulti.m
l1QPSMO.m
l1QPSMOMulti.m
learnCurve.m
leaveMOut.m
lineSearchNNLS.m
lineSearchSRC2.m
localSVM.m
log2Inf.m
lrc.m
mat2vec.m
matrixNorm.m
matrizicing.m
mergeOption.m
multiClassifiers.m
nearestCentroidPredict.m
nearestCentroidTrain.m
nnlsClassifier.m
nnlsClassifierLargeSampleSize.m
NNLSKernelBatch.m
NNQPActiveSet.m
NNQPIP.m
NNQPIPMulti.m
NNQPSMO.m
NNQPSMOMulti.m
normalizeKernelMatrix.m
normcl1.m
normmean0std1.m
perform.m
plotBarError.m
plotDataMulti.m
plotNemenyiTest.m
plotTime.m
proximalOperator.m
pseudoinverse.m
readMe.txt
sampleSelKNN.m
sampleSelNNLS.m
significantAcc.m
softSVMPredict2.m
softSVMTrain2.m
sparsenmfnnlstest.m
sparsity.m
src.m
SRC2.m
subspace.m
threeDSearchUniverse.m
unmatrizicing.m
usr.m
vec2mat.m
vote.m
vsmf.m
wvote.m