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.


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


1.5.1 by Pete Mohanty, 6 months ago


Report a bug at https://github.com/rdrr1990/kerasformula/issues

Browse source code at https://github.com/cran/kerasformula

Authors: Pete Mohanty [aut, cre]

Documentation:   PDF Manual  

GPL (>= 2) license

Imports ggplot2

Depends on keras, dplyr, Matrix

Suggests tensorflow, knitr

See at CRAN