My Little Pony
Fully connected feed forward network with dropout after each activation function. The features can either be a single lazy_tensor or one or more numeric columns (but not both).
This Learner can be instantiated using the sugar function lrn():
lrn("classif.mlp", ...)
lrn("regr.mlp", ...)
Supported task types: 'classif', 'regr'
Predict Types:
Feature Types: integer , numeric , lazy_tensor
Required Packages: list("mlr3"), list("mlr3torch"), list("torch")
Parameters from LearnerTorch, as well as:
activation :: [nn_module]
The activation function. Is initialized to nn_relu.
activation_args :: named list()
A named list with initialization arguments for the activation function. This is intialized to an empty list.
neurons :: integer()
The number of neurons per hidden layer. By default there is no hidden layer. Setting this to c(10, 20) would have a the first hidden layer with 10 neurons and the second with 20.
n_layers :: integer()
The number of layers. This parameter must only be set when neurons has length 1.
p :: numeric(1)
The dropout probability. Is initialized to 0.5.
shape :: integer() or NULL
The input shape of length 2, e.g. c(NA, 5). Only needs to be present when there is a lazy tensor input with unknown shape (NULL). Otherwise the input shape is inferred from the number of numeric features.
# Define the Learner and set parameter values learner = lrn("classif.mlp") learner$param_set$set_values( epochs = 1, batch_size = 16, device = "cpu", neurons = 10 ) # Define a Task task = tsk("iris") # Create train and test set ids = partition(task) # Train the learner on the training ids learner$train(task, row_ids = ids$train) # Make predictions for the test rows predictions = learner$predict(task, row_ids = ids$test) # Score the predictions predictions$score()
Gorishniy Y, Rubachev I, Khrulkov V, Babenko A (2021). Revisiting Deep Learning for Tabular Data.
arXiv, 2106.11959 .
Other Learner: mlr_learners.tab_resnet, mlr_learners.torch_featureless, mlr_learners_torch, mlr_learners_torch_image, mlr_learners_torch_model
mlr3::Learner -> mlr3torch::LearnerTorch -> LearnerTorchMLP
new()Creates a new instance of this R6 class.
LearnerTorchMLP$new(
task_type,
optimizer = NULL,
loss = NULL,
callbacks = list()
)
task_type: (character(1))
The task type, either `"classif`" or `"regr"`.
optimizer: (TorchOptimizer)
The optimizer to use for training. Per default, **adam** is used.
loss: (TorchLoss)
The loss used to train the network. Per default, **mse** is used for regression and **cross_entropy** for classification.
callbacks: (list() of TorchCallbacks)
The callbacks. Must have unique ids.
clone()The objects of this class are cloneable with this method.
LearnerTorchMLP$clone(deep = FALSE)
deep: Whether to make a deep clone.
Useful links