MLPRegressor

Multi Layer Perceptron Network (MLP), as described in [1].

Quickstart

from sktime.regression.deep_learning.mlp import MLPRegressor

estimator = MLPRegressor(n_epochs=2000, batch_size=16, callbacks=None, verbose=False, loss='mean_squared_error', metrics=None, random_state=None, activation='linear', activation_hidden='relu', use_bias=True, optimizer=None, dropout=(0.1, 0.2, 0.2, 0.3), n_layers=3, hidden_dim=500)

Parameters(15)

should inherited fields be listed here?

n_epochsint, default = 2000

the number of epochs to train the model

batch_sizeint, default = 16

the number of samples per gradient update.

callbackslist of keras.callbacks.Callback, optional (default=None)

List of Keras callbacks to apply during model training.

random_stateint or None, default=None

Seed for random number generation.

verboseboolean, default = False

whether to output extra information

lossstring, default=”mean_squared_error”

fit parameter for the keras model

metricslist of strings, default=[“accuracy”],

activationstring or a tf callable, default=”linear”

Activation function used in the output layer. List of available activation functions: https://keras.io/api/layers/activations/

activation_hiddenstring or a tf callable, default=”relu”

Activation function used in the hidden layers. List of available activation functions: https://keras.io/api/layers/activations/

use_biasboolean, default = True

whether the layer uses a bias vector.

optimizerkeras.optimizers object, default = Adam(lr=0.01)

specify the optimizer and the learning rate to be used.

dropoutfloat or tuple, default=(0.1, 0.2, 0.2, 0.3)

The dropout rate for the hidden layers. If float, the same rate is used for all layers. If tuple, length must equal n_layers + 1, where the first n_layers elements correspond to dropout applied before each hidden Dense layer, and the last element corresponds to the dropout applied after the final hidden layer (before the output layer).

n_layersint, default=3

Number of hidden Dense layers in the MLP.

hidden_dimint or tuple, default=500

Number of units in each hidden Dense layer. If int, the same number of units is used for all hidden layers. If list or tuple, length must equal n_layers, with each element specifying the number of units for the corresponding hidden layer.

Examples

>>> from sktime.datasets import load_unit_test
>>> from sktime.regression.deep_learning.mlp import MLPRegressor
>>> X_train, y_train = load_unit_test (return_X_y = True, split = "train")
>>> X_test, y_test = load_unit_test (return_X_y = True, split = "test")
>>> regressor = MLPRegressor ()
>>> regressor. fit (X_train, y_train) MLPRegressor(
... )
>>> y_pred = regressor. predict (X_test)

References

1. [1 ] Wang et al, Time series classification from scratch with deep neural networks: A strong baseline, International joint conference on neural networks (IJCNN), 2017.