Package smile.regression

Class MLP

java.lang.Object

smile.base.mlp.MultilayerPerceptron

smile.regression.MLP

All Implemented Interfaces:

Serializable, ToDoubleFunction<double[]>, Regression<double[]>

public class MLP
extends MultilayerPerceptron
implements Regression<double[]>

Fully connected multilayer perceptron neural network for regression. An MLP consists of at least three layers of nodes: an input layer, a hidden layer and an output layer. The nodes are interconnected through weighted acyclic arcs from each preceding layer to the following, without lateral or feedback connections. Each node calculates a transformed weighted linear combination of its inputs (output activations from the preceding layer), with one of the weights acting as a trainable bias connected to a constant input. The transformation, called activation function, is a bounded non-decreasing (non-linear) function.

See Also:

• Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface smile.regression.Regression

Regression.Trainer<T,M extends Regression<T>>

Field Summary

Fields inherited from class smile.base.mlp.MultilayerPerceptron

clipNorm, clipValue, epsilon, lambda, learningRate, momentum, net, output, p, rho, t, target

Constructor Summary

Constructors

Constructor	Description
MLP(LayerBuilder... builders)	Constructor.
MLP(Scaler scaler, LayerBuilder... builders)	Constructor.

Method Summary

Modifier and Type	Method	Description
static MLP	fit(double[][] x, double[] y, Properties params)	Fits a MLP model.
boolean	online()	Returns true if this is an online learner.
double	predict(double[] x)	Predicts the dependent variable of an instance.
void	update(double[][] x, double[] y)	Updates the model with a mini-batch.
void	update(double[] x, double y)	Updates the model with a single sample.

Methods inherited from class smile.base.mlp.MultilayerPerceptron

backpropagate, getClipNorm, getClipValue, getLearningRate, getMomentum, getWeightDecay, propagate, setClipNorm, setClipValue, setLearningRate, setMomentum, setParameters, setRMSProp, setWeightDecay, toString, update

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface smile.regression.Regression

applyAsDouble, predict, predict, predict, update

Constructor Details

MLP

public MLP(LayerBuilder... builders)

Constructor.

Parameters:

builders - the builders of input and hidden layers from bottom to top.

MLP

public MLP(Scaler scaler,
 LayerBuilder... builders)

Constructor.

Parameters:

scaler - the scaling function of output values.

builders - the builders of input and hidden layers from bottom to top.

Method Details

predict

public double predict(double[] x)

Description copied from interface: Regression

Predicts the dependent variable of an instance.

Specified by:

predict in interface Regression<double[]>

Parameters:

x - an instance.

Returns:

the predicted value of dependent variable.

online

public boolean online()

Description copied from interface: Regression

Returns true if this is an online learner.

Specified by:

online in interface Regression<double[]>

Returns:

true if online learner.

update

public void update(double[] x,
 double y)

Updates the model with a single sample. RMSProp is not applied.

Specified by:

update in interface Regression<double[]>

Parameters:

x - the training instance.

y - the response variable.

update

public void update(double[][] x,
 double[] y)

Updates the model with a mini-batch. RMSProp is applied if rho > 0.

Specified by:

update in interface Regression<double[]>

Parameters:

x - the training instances.

y - the response variables.

fit

public static MLP fit(double[][] x,
 double[] y,
 Properties params)

Fits a MLP model.

Parameters:

x - the training dataset.

y - the response variable.

params - the hyper-parameters.

Returns:

the model.