The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

neuralnetwork

neuralnetwork fits compact multilayer perceptrons for everyday R workflows: formula input, tabular data, regression, classification, tuning, cross validation, and readable model objects. It is designed for problems where nnet feels too small, neuralnet feels too manual, and a full deep-learning framework would be more machinery than the job needs.

Install

install.packages("neuralnetwork")

To install the local source tarball:

install.packages("neuralnetwork_0.1.0.tar.gz", repos = NULL, type = "source")

Quick Start

library(neuralnetwork)

fit <- nn_fit(
  Species ~ .,
  data = iris,
  hidden = "auto",
  optimizer = "auto",
  epochs = 20,
  validation_split = 0.2,
  seed = 1,
  verbose = FALSE
)

fit
predict(fit, iris[1:5, ], type = "class")
round(predict(fit, iris[1:5, ], type = "prob"), 3)

ev <- nn_evaluate(fit, iris)
ev

The printed model gives the architecture, optimizer, loss, backend, training length, final training score, and validation score when available. The evaluation object prints metrics as a small table and includes the confusion matrix for classification.

Regression

Regression uses the same interface. Targets can be scaled during training and returned on the original scale for prediction.

fit_reg <- nn_fit(
  mpg ~ wt + hp + disp,
  data = mtcars,
  hidden = c(8, 4),
  optimizer = "adam",
  epochs = 40,
  batch_size = 8,
  learning_rate = 0.01,
  validation_split = 0.2,
  seed = 2,
  verbose = FALSE
)

predict(fit_reg, mtcars[1:5, ])
nn_evaluate(fit_reg, mtcars)

For regression problems with outliers, use Huber loss:

fit_huber <- nn_fit(
  mpg ~ wt + hp + disp,
  data = mtcars,
  hidden = c(8, 4),
  optimizer = "adam",
  loss = "huber",
  huber_delta = 1,
  epochs = 40,
  batch_size = 8,
  learning_rate = 0.01,
  seed = 3,
  verbose = FALSE
)

Choosing Settings

Good first defaults:

• hidden = "auto" for a compact task-aware architecture.
• optimizer = "auto" for L-BFGS on small deterministic problems and Adam when using stochastic features such as dropout or callbacks.
• validation_split = 0.2 when you want validation loss, early stopping, or validation-based tuning.
• metric = "balanced_accuracy" for imbalanced classification, metric = "f1" when the positive class matters, and metric = "mae" or metric = "rmse" for regression.
• loss = "huber" for regression data where outliers may dominate squared error.

Tuning and Validation

tuned <- nn_tune(
  Species ~ .,
  data = iris,
  grid = list(
    hidden = list(4, c(6, 3)),
    learning_rate = c(0.01, 0.003)
  ),
  metric = "balanced_accuracy",
  epochs = 8,
  validation_split = 0.2,
  seed = 4,
  verbose = FALSE
)

tuned
tuned$best_model

cv <- nn_cv(
  Species ~ .,
  data = iris,
  k = 3,
  metric = "f1",
  hidden = 4,
  epochs = 5,
  seed = 5,
  verbose = FALSE
)

cv

Feature Importance

imp <- nn_permutation_importance(
  fit_reg,
  mtcars,
  metric = "mae",
  n_repeats = 3,
  seed = 6
)

imp

Function Map

What Is Included

• Formula, data frame, matrix, and vector inputs.
• Regression, binary classification, and multiclass classification.
• Multiple hidden layers, including hidden = 0 for no hidden layer.
• Adam, SGD, momentum, Nesterov, RPROP, GRPROP, and L-BFGS optimizers.
• Automatic hidden-layer sizing, activation choice, and optimizer choice.
• Portable Rcpp forward-pass kernels when available.
• Dropout, L2 regularization, gradient clipping, learning-rate decay, validation splits, early stopping, and callbacks.
• Sample weights and balanced class weights.
• Huber loss for robust regression.
• Accuracy, balanced accuracy, macro F1, log loss, RMSE, MAE, and R-squared.
• Tuning, repeated k-fold cross-validation, permutation importance, save/load helpers, and S3 predict(), print(), plot(), summary(), and coef().
• Compatibility helpers for common nnet and neuralnet workflows: nn_multinom(), nn_class_ind(), nn_which_is_max(), nn_compute(), nn_generalized_weights(), nn_gwplot(), nn_hessian(), and nn_confint().

See vignette("neuralnetwork") for a fuller walkthrough.

For reference-style help inside R, see ?neuralnetwork, ?neuralnetwork-metrics, ?neuralnetwork-callbacks, and ?neuralnetwork-objects.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.