kerasformula: A High-Level R Interface for Neural Nets

Adds a high-level interface for 'keras' neural nets. kms() fits neural net and accepts R formulas to aid data munging and hyperparameter selection. kms() can optionally accept a compiled keras_sequential_model() from 'keras'. kms() accepts a number of parameters (like loss and optimizer) and splits the data into (optionally sparse) test and training matrices. kms() facilitates setting advanced hyperparameters (e.g., regularization). kms() returns a single object with predictions, a confusion matrix, and function call details.

Version: 1.5.0
Depends: keras, dplyr, Matrix
Imports: ggplot2
Suggests: tensorflow, knitr
Published: 2018-08-14
Author: Pete Mohanty [aut, cre]
Maintainer: Pete Mohanty <pete.mohanty at gmail.com>
BugReports: https://github.com/rdrr1990/kerasformula/issues
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
URL: https://github.com/rdrr1990/kerasformula
NeedsCompilation: yes
CRAN checks: kerasformula results

Downloads:

Reference manual: kerasformula.pdf
Vignettes: kerasformula
Package source: kerasformula_1.5.0.tar.gz
Windows binaries: r-devel: kerasformula_1.5.0.zip, r-release: kerasformula_1.5.0.zip, r-oldrel: kerasformula_1.0.0.zip
OS X binaries: r-release: kerasformula_1.5.0.tgz, r-oldrel: kerasformula_1.5.0.tgz
Old sources: kerasformula archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=kerasformula to link to this page.