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.

Total

3,507

Last month

651

Last week

118

Average per day

22

Daily downloads

Total downloads

Description file content

Package
kerasformula
Type
Package
Title
A High-Level R Interface for Neural Nets
Version
1.5.1
Author
Pete Mohanty [aut, cre]
Maintainer
Pete Mohanty
Description
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.
License
GPL (>= 2)
Encoding
UTF-8
LazyData
true
RoxygenNote
6.0.1
VignetteBuilder
knitr
URL
BugReports
https://github.com/rdrr1990/kerasformula/issues
Depends
keras, dplyr, Matrix
Imports
ggplot2
Suggests
tensorflow, knitr
NeedsCompilation
yes
Packaged
2018-08-23 17:28:44 UTC; mohanty
Repository
CRAN
Date/Publication
2018-08-23 17:52:14 UTC

install.packages('kerasformula')

1.5.1

28 days ago

https://github.com/rdrr1990/kerasformula

Pete Mohanty

GPL (>= 2)

Depends on

keras, dplyr, Matrix

Imports

ggplot2

Suggests

tensorflow, knitr

Discussions