smile.base.mlp

Class MultilayerPerceptron

java.lang.Object

smile.base.mlp.MultilayerPerceptron

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

MLP, MLP

public abstract class MultilayerPerceptron
extends java.lang.Object
implements java.io.Serializable

Fully connected multilayer perceptron neural network. 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

Field Summary

Fields

Modifier and Type	Field and Description
protected double	alpha momentum factor
protected double	eta learning rate
protected double	lambda weight decay factor, which is also a regularization term.
protected Layer[]	net The hidden layers.
protected OutputLayer	output The output layer.
protected int	p The dimensionality of input data.
protected double[]	target The buffer to store desired target value of training instance.

Constructor Summary

Constructors

Constructor and Description
MultilayerPerceptron(Layer... net) Constructor.

Method Summary

Modifier and Type	Method and Description
protected void	backpropagate(double[] x) Propagates the errors back through the network.
double	getLearningRate() Returns the learning rate.
double	getMomentum() Returns the momentum factor.
double	getWeightDecay() Returns the weight decay factor.
protected void	propagate(double[] x) Propagates the signals through the neural network.
void	setLearningRate(double eta) Sets the learning rate.
void	setMomentum(double alpha) Sets the momentum factor.
void	setWeightDecay(double lambda) Sets the weight decay factor.
java.lang.String	toString()
protected void	update() Updates the weights.

Methods inherited from class java.lang.Object

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

Field Detail

p

protected int p

The dimensionality of input data.

output

protected OutputLayer output

The output layer.

net

protected Layer[] net

The hidden layers.

target

protected double[] target

The buffer to store desired target value of training instance.

eta

protected double eta

learning rate

alpha

protected double alpha

momentum factor

lambda

protected double lambda

weight decay factor, which is also a regularization term.

Constructor Detail

MultilayerPerceptron

public MultilayerPerceptron(Layer... net)

Constructor.

Parameters:

net - the layers from bottom to top. The input layer should not be included.

Method Detail

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

setLearningRate

public void setLearningRate(double eta)

Sets the learning rate.

Parameters:

eta - the learning rate.

setMomentum

public void setMomentum(double alpha)

Sets the momentum factor. alpha = 0.0 means no momentum.

Parameters:

alpha - the momentum factor.

setWeightDecay

public void setWeightDecay(double lambda)

Sets the weight decay factor. After each weight update, every weight is simply "decayed" or shrunk according to w = w * (1 - 2 * eta * lambda).

getLearningRate

public double getLearningRate()

Returns the learning rate.

getMomentum

public double getMomentum()

Returns the momentum factor.

getWeightDecay

public double getWeightDecay()

Returns the weight decay factor.

propagate

protected void propagate(double[] x)

Propagates the signals through the neural network.

backpropagate

protected void backpropagate(double[] x)

Propagates the errors back through the network.

update

protected void update()

Updates the weights.