autoencoder: Sparse Autoencoder for Automatic Learning of Representative Features from Unlabeled Data

Implementation of the sparse autoencoder in R environment, following the notes of Andrew Ng (http://www.stanford.edu/class/archive/cs/cs294a/cs294a.1104/sparseAutoencoder.pdf). The features learned by the hidden layer of the autoencoder (through unsupervised learning of unlabeled data) can be used in constructing deep belief neural networks.

Author
Eugene Dubossarsky (project leader, chief designer), Yuriy Tyshetskiy (design, implementation, testing)
Date of publication
2015-07-02 09:09:12
Maintainer
Yuriy Tyshetskiy <yuriy.tyshetskiy@nicta.com.au>
License
GPL-2
Version
1.1

View on CRAN

Man pages

autoencode
Train a sparse autoencoder using unlabeled data
autoencoder_Ninput=100_Nhidden=100_rho=1e-2
A trained autoencoder example with 100 hidden units
autoencoder_Ninput=100_Nhidden=25_rho=1e-2
A trained autoencoder example with 25 hidden units
autoencoder-package
Implementation of sparse autoencoder for automatic learning...
predict.autoencoder
Predict outputs of a sparse autoencoder
training_matrix_N=1e4_Ninput=100
An example training set of images for training sparse...
visualize.hidden.units
Visualize features learned by a sparse autoencoder

Files in this package

autoencoder
autoencoder/NAMESPACE
autoencoder/data
autoencoder/data/autoencoder_Ninput=100_Nhidden=25_rho=1e-2.rda
autoencoder/data/autoencoder_Ninput=100_Nhidden=100_rho=1e-2.rda
autoencoder/data/datalist
autoencoder/data/training_matrix_N=5e3_Ninput=100.rda
autoencoder/R
autoencoder/R/autoencoder.R
autoencoder/MD5
autoencoder/DESCRIPTION
autoencoder/man
autoencoder/man/autoencode.Rd
autoencoder/man/autoencoder_Ninput=100_Nhidden=25_rho=1e-2.Rd
autoencoder/man/autoencoder_Ninput=100_Nhidden=100_rho=1e-2.Rd
autoencoder/man/visualize.hidden.units.Rd
autoencoder/man/autoencoder-package.Rd
autoencoder/man/training_matrix_N=1e4_Ninput=100.Rd
autoencoder/man/predict.autoencoder.Rd