Module ojalgo

Package org.ojalgo.ann

Class ArtificialNeuralNetwork

java.lang.Object

org.ojalgo.ann.ArtificialNeuralNetwork

public final class ArtificialNeuralNetwork
extends Object

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static enum	ArtificialNeuralNetwork.Activator	https://en.wikipedia.org/wiki/Activation_function
static enum	ArtificialNeuralNetwork.Error

Method Summary

Modifier and Type	Method	Description
static NetworkBuilder	builder(int numberOfNetworkInputNodes)
static NetworkTrainer	builder(int numberOfInputNodes, int... nodesPerCalculationLayer)	Deprecated. Use builder(int) instead
static NetworkBuilder	builder(PhysicalStore.Factory<Double,?> factory, int numberOfNetworkInputNodes)
static NetworkTrainer	builder(PhysicalStore.Factory<Double,?> factory, int numberOfInputNodes, int... nodesPerCalculationLayer)	Deprecated. Use builder(org.ojalgo.matrix.store.PhysicalStore.Factory, int) instead
int	depth()
boolean	equals(Object obj)
static ArtificialNeuralNetwork	from(DataInput input)	Read (reconstruct) an ANN from the specified input previously written by writeTo(DataOutput).
static ArtificialNeuralNetwork	from(File file)
static ArtificialNeuralNetwork	from(Path path, OpenOption... options)
static ArtificialNeuralNetwork	from(PhysicalStore.Factory<Double,?> factory, DataInput input)	Read (reconstruct) an ANN from the specified input previously written by writeTo(DataOutput).
static ArtificialNeuralNetwork	from(PhysicalStore.Factory<Double,?> factory, File file)
static ArtificialNeuralNetwork	from(PhysicalStore.Factory<Double,?> factory, Path path, OpenOption... options)
ArtificialNeuralNetwork.Activator	getActivator(int layer)
double	getBias(int layer, int output)
double	getWeight(int layer, int input, int output)
int	hashCode()
NetworkInvoker	newInvoker()	With batch size 1
NetworkInvoker	newInvoker(int batchSize)	If you create multiple invokers you can use them in different threads simutaneously - the invoker contains any/all invocation specific state.
NetworkTrainer	newTrainer()	With batch size 1
NetworkTrainer	newTrainer(int batchSize)	Only 1 trainer at the time.
Structure2D[]	structure()
String	toString()
int	width()
void	writeTo(DataOutput output)	Will write (save) the ANN to the specified output.
void	writeTo(File file)
void	writeTo(Path path, OpenOption... options)

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Method Details

builder

public static NetworkBuilder builder(int numberOfNetworkInputNodes)

builder

@Deprecated
public static NetworkTrainer builder(int numberOfInputNodes,
 int... nodesPerCalculationLayer)

Deprecated.

Use builder(int) instead

builder

public static NetworkBuilder builder(PhysicalStore.Factory<Double,?> factory,
 int numberOfNetworkInputNodes)

builder

@Deprecated
public static NetworkTrainer builder(PhysicalStore.Factory<Double,?> factory,
 int numberOfInputNodes,
 int... nodesPerCalculationLayer)

Deprecated.

Use builder(org.ojalgo.matrix.store.PhysicalStore.Factory, int) instead

from

public static ArtificialNeuralNetwork from(DataInput input)
                                    throws IOException

Read (reconstruct) an ANN from the specified input previously written by writeTo(DataOutput).

Throws:

IOException

from

public static ArtificialNeuralNetwork from(File file)

See Also:

• from(DataInput)

from

public static ArtificialNeuralNetwork from(Path path,
 OpenOption... options)

See Also:

• from(DataInput)

from

public static ArtificialNeuralNetwork from(PhysicalStore.Factory<Double,?> factory,
 DataInput input)
                                    throws IOException

Read (reconstruct) an ANN from the specified input previously written by writeTo(DataOutput).

Throws:

IOException

from

public static ArtificialNeuralNetwork from(PhysicalStore.Factory<Double,?> factory,
 File file)

See Also:

• from(DataInput)

from

public static ArtificialNeuralNetwork from(PhysicalStore.Factory<Double,?> factory,
 Path path,
 OpenOption... options)

See Also:

• from(DataInput)

depth

public int depth()

Returns:

The number of calculation layers

equals

public boolean equals(Object obj)

Overrides:

equals in class Object

getActivator

public ArtificialNeuralNetwork.Activator getActivator(int layer)

getBias

public double getBias(int layer,
 int output)

getWeight

public double getWeight(int layer,
 int input,
 int output)

hashCode

public int hashCode()

Overrides:

hashCode in class Object

newInvoker

public NetworkInvoker newInvoker()

With batch size 1

See Also:

• newInvoker(int)

newInvoker

public NetworkInvoker newInvoker(int batchSize)

If you create multiple invokers you can use them in different threads simutaneously - the invoker contains any/all invocation specific state.

Parameters:

batchSize - The batch size - the number of batched invocations

Returns:

The invoker

newTrainer

public NetworkTrainer newTrainer()

With batch size 1

See Also:

• newTrainer(int)

newTrainer

public NetworkTrainer newTrainer(int batchSize)

Only 1 trainer at the time.

Parameters:

batchSize - The batch size - the number of batched training examples

Returns:

The trainer

structure

public Structure2D[] structure()

toString

public String toString()

Overrides:

toString in class Object

width

public int width()

Returns:

The max number of nodes in any layer

writeTo

public void writeTo(DataOutput output)
             throws IOException

Will write (save) the ANN to the specified output. Can then later be read back by using from(DataInput).

Throws:

IOException

writeTo

public void writeTo(File file)

See Also:

• writeTo(DataOutput)

writeTo

public void writeTo(Path path,
 OpenOption... options)

See Also:

• writeTo(DataOutput)