文件名称：UFLDL exercise8 Linear Decoder
文件大小：36.63MB
文件格式：ZIP
更新时间：2019-05-03 17:15:30
UFLDL
In this exercise, you will implement a linear decoder (a sparse autoencoder whose output layer uses a linear activation function). You will then apply it to learn features on color images from the STL-10 dataset. These features will be used in an later exercise on convolution and pooling for classifying STL-10 images.
【文件预览】：
linear_decoder_exercise
----computeNumericalGradient.m(1KB)
----STL10Features.mat(1.4MB)
----linearDecoderExercise.m(5KB)
----sparseAutoencoderLinearCost.m(4KB)
----stl10_patches_100k()
--------stlSampledPatches.mat(35.91MB)
----initializeParameters.m(622B)
----displayColorNetwork.m(1KB)
----minFunc()
--------lbfgsC.mexmac(9KB)
--------lbfgsUpdate.m(614B)
--------autoHess.m(901B)
--------minFunc_processInputOptions.m(4KB)
--------mcholC.mexw64(12KB)
--------ArmijoBacktrack.m(3KB)
--------conjGrad.m(2KB)
--------example_minFunc_LR.m(2KB)
--------precondDiag.m(42B)
--------lbfgsC.mexw32(7KB)
--------autoHv.m(317B)
--------autoGrad.m(807B)
--------lbfgsC.mexmaci(12KB)
--------lbfgsC.c(2KB)
--------mcholC.mexw32(8KB)
--------precondTriuDiag.m(60B)
--------autoTensor.m(870B)
--------lbfgsC.mexa64(8KB)
--------precondTriu.m(51B)
--------lbfgsC.mexw64(10KB)
--------callOutput.m(385B)
--------WolfeLineSearch.m(11KB)
--------rosenbrock.m(1KB)
--------lbfgs.m(924B)
--------dampedUpdate.m(995B)
--------mcholC.mexmaci64(13KB)
--------minFunc.m(43KB)
--------logistic()
--------lbfgsC.mexmaci64(9KB)
--------mcholinc.m(564B)
--------lbfgsC.mexglx(8KB)
--------isLegal.m(107B)
--------taylorModel.m(677B)
--------example_minFunc.m(2KB)
--------polyinterp.m(4KB)
--------mchol.m(1KB)
--------mcholC.c(4KB)