Package deepnetts.automl

Class FeedForwardNetworkFactory

java.lang.Object

deepnetts.automl.FeedForwardNetworkFactory

All Implemented Interfaces:

NetworkFactory<FeedForwardNetwork>

public class FeedForwardNetworkFactory
extends Object
implements NetworkFactory<FeedForwardNetwork>

Factory for FeedForwardNetwork. Creates a FeedForward neural network with specified settings. It is used by AutoML to create various network architectures.

See Also:

• FeedForwardNetwork

Constructor Summary

Constructors

Constructor	Description
FeedForwardNetworkFactory()

Method Summary

Modifier and Type	Method	Description
FeedForwardNetwork	createNeuralNetwork(Properties params)	Creates and returns a neural network of specified type
void	setHiddenActivation(ActivationType hiddenActivation)
void	setLossType(LossType lossType)
void	setNumInputs(int numInputs)
void	setNumOutputs(int numOutputs)
void	setOutputActivation(ActivationType outputActivation)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

FeedForwardNetworkFactory

public FeedForwardNetworkFactory()

Method Details

createNeuralNetwork

public FeedForwardNetwork createNeuralNetwork(Properties params)

Description copied from interface: NetworkFactory

Creates and returns a neural network of specified type

Specified by:

createNeuralNetwork in interface NetworkFactory<FeedForwardNetwork>

Parameters:

params - properties of a neural network to create

Returns:

neural network of specified type

setNumInputs

public void setNumInputs(int numInputs)

setNumOutputs

public void setNumOutputs(int numOutputs)

setLossType

public void setLossType(LossType lossType)

setHiddenActivation

public void setHiddenActivation(ActivationType hiddenActivation)

setOutputActivation

public void setOutputActivation(ActivationType outputActivation)