smile.base.mlp

Class OutputLayer

java.lang.Object

smile.base.mlp.Layer

smile.base.mlp.OutputLayer

All Implemented Interfaces:

java.io.Serializable

public class OutputLayer
extends Layer

The output layer in the neural network.

See Also:

Serialized Form

Field Summary

Fields inherited from class smile.base.mlp.Layer

delta, gradient, n, output, p, update, weight

Constructor Summary

Constructors

Constructor and Description
OutputLayer(int n, int p, OutputFunction f, Cost cost) Constructor.

Method Summary

Modifier and Type	Method and Description
void	backpropagate(double[] error) Propagates the errors back to a lower layer.
void	computeError(double[] target, double weight) Compute the network output error.
Cost	cost() Returns the cost function of neural network.
void	f(double[] x) The activation or output function.
java.lang.String	toString()

Methods inherited from class smile.base.mlp.Layer

computeUpdate, getInputSize, getOutputSize, gradient, linear, mle, mse, output, propagate, rectifier, sigmoid, tanh, update

Methods inherited from class java.lang.Object

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

Constructor Detail

OutputLayer

public OutputLayer(int n,
                   int p,
                   OutputFunction f,
                   Cost cost)

Constructor.

Parameters:

n - the number of neurons.

p - the number of input variables (not including bias value).

f - the output function.

cost - the cost function.

Method Detail

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

cost

public Cost cost()

Returns the cost function of neural network.

f

public void f(double[] x)

Description copied from class: Layer

The activation or output function.

Specified by:

f in class Layer

Parameters:

x - the input and output values.

backpropagate

public void backpropagate(double[] error)

Description copied from class: Layer

Propagates the errors back to a lower layer.

Specified by:

backpropagate in class Layer

Parameters:

error - the gradient vector of lower layer.

computeError

public void computeError(double[] target,
                         double weight)

Compute the network output error.

Parameters:

target - the desired output.

weight - a positive weight value associated with the training instance.