Sparse Autoencoder for Automatic Learning of Representative Features from Unlabeled Data
Released Jul 2, 2015 by Eugene Dubossarsky (project leader, chief designer), Yuriy Tyshetskiy (design, implementation, testing)
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.
This package can be included as a dependency from a Java or Scala project by including
the following your project's
about embedding Renjin in JVM-based projects.
<dependencies> <dependency> <groupId>org.renjin.cran</groupId> <artifactId>autoencoder</artifactId> <version>1.1-b31</version> </dependency> </dependencies> <repositories> <repository> <id>bedatadriven</id> <name>bedatadriven public repo</name> <url>https://nexus.bedatadriven.com/content/groups/public/</url> </repository> </repositories>
If you're using Renjin from the command line, you load this library by invoking:
This package was last tested against Renjin 0.8.2523 on Nov 11, 2017.