Package smile.base.mlp

Class OutputLayer

java.lang.Object

smile.base.mlp.Layer

smile.base.mlp.OutputLayer

All Implemented Interfaces:

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

bias, biasGradient, biasGradientMoment1, biasGradientMoment2, biasUpdate, dropout, mask, n, output, outputGradient, p, weight, weightGradient, weightGradientMoment1, weightGradientMoment2, weightUpdate

Constructor Summary

Constructors

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

Method Summary

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

Methods inherited from class smile.base.mlp.Layer

backpopagateDropout, builder, computeGradient, computeGradientUpdate, getInputSize, getOutputSize, gradient, input, input, leaky, leaky, leaky, linear, linear, mle, mse, of, output, propagate, propagateDropout, rectifier, rectifier, sigmoid, sigmoid, tanh, tanh, update

Methods inherited from class java.lang.Object

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

Constructor Details

OutputLayer

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

Constructor.

Parameters:

n - the number of neurons.

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

activation - the output activation function.

cost - the cost function.

Method Details

toString

public String toString()

Overrides:

toString in class Object

cost

public Cost cost()

Returns the cost function of neural network.

Returns:

the cost function.

transform

public void transform(double[] x)

Description copied from class: Layer

The activation or output function.

Specified by:

transform in class Layer

Parameters:

x - the input and output values.

backpropagate

public void backpropagate(double[] lowerLayerGradient)

Description copied from class: Layer

Propagates the errors back to a lower layer.

Specified by:

backpropagate in class Layer

Parameters:

lowerLayerGradient - the gradient vector of lower layer.

computeOutputGradient

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

Compute the network output gradient.

Parameters:

target - the desired output.

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