Package me.yixqiao.jlearn.layers

Class InputLayer

java.lang.Object

me.yixqiao.jlearn.layers.Layer

me.yixqiao.jlearn.layers.InputLayer

All Implemented Interfaces:

java.io.Serializable

public class InputLayer
extends Layer

Layer for input.

Basically all functions are no-ops.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor	Description
InputLayer(int size)	Create an input layer.

Method Summary

Modifier and Type	Method	Description
Layer	cloneLayer()	Clone the layer, including weights and biases.
InputLayer	cloneSettings()	Clone the settings.
Matrix	forwardPropagate(Matrix x)	No op forward propagation.
Activation	getActivation()	Return a linear activation.
Matrix	getErrors(Matrix prevErrors)	No op.
Matrix	getErrorsExpected(Matrix y)	No op.
int	getOutSize()	Get the output size of the layer.
void	initLayer(int prevSize, Activation prevActivation)	No op.
void	setOptimizers(Optimizer wOptimizer, Optimizer bOptimizer)	No op.
java.lang.String	toString()	Get a string representation.
void	update(Matrix errors)	No op.

Methods inherited from class java.lang.Object

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

Constructor Detail

InputLayer

public InputLayer(int size)

Create an input layer.

Parameters:

size - size of the input

Method Detail

initLayer

public void initLayer(int prevSize,
                      Activation prevActivation)

No op.

Specified by:

initLayer in class Layer

Parameters:

prevSize - size of the previous layer (can be anything)

prevActivation - activation function or previous layer

getActivation

public Activation getActivation()

Return a linear activation.

Specified by:

getActivation in class Layer

Returns:

a new linear activation

getOutSize

public int getOutSize()

Description copied from class: Layer

Get the output size of the layer.

Specified by:

getOutSize in class Layer

Returns:

the output size

forwardPropagate

public Matrix forwardPropagate(Matrix x)

No op forward propagation.

Specified by:

forwardPropagate in class Layer

Parameters:

x - input matrix

Returns:

the same input matrix

setOptimizers

public void setOptimizers(Optimizer wOptimizer,
                          Optimizer bOptimizer)

No op.

Specified by:

setOptimizers in class Layer

Parameters:

wOptimizer - optimizer for weights

bOptimizer - optimizer for biases

cloneLayer

public Layer cloneLayer()

Description copied from class: Layer

Clone the layer, including weights and biases.

Specified by:

cloneLayer in class Layer

Returns:

the clone

getErrors

public Matrix getErrors(Matrix prevErrors)

No op.

Specified by:

getErrors in class Layer

Parameters:

prevErrors - errors from previous layer (layer after output)

Returns:

null

getErrorsExpected

public Matrix getErrorsExpected(Matrix y)

No op.

Specified by:

getErrorsExpected in class Layer

Parameters:

y - expected outputs

Returns:

null

update

public void update(Matrix errors)

No op. Nothing is updated.

Specified by:

update in class Layer

Parameters:

errors - calculated errors

toString

public java.lang.String toString()

Description copied from class: Layer

Get a string representation.

Specified by:

toString in class Layer

Returns:

the string

cloneSettings

public InputLayer cloneSettings()

Description copied from class: Layer

Clone the settings.

This will return a layer with the same size and activation, but with randomly initialized weights and biases.

Specified by:

cloneSettings in class Layer

Returns:

the clone