MultilayerPerceptron (GridGain 8.9.14)

java.lang.Object
- org.apache.ignite.ml.nn.MultilayerPerceptron

All Implemented Interfaces:

Serializable, AutoCloseable, IgniteModel<Matrix,Matrix>, Model<Matrix,Matrix>, Parametrized<MultilayerPerceptron>, SmoothParametrized<MultilayerPerceptron>
```
public final class MultilayerPerceptron
extends Object
implements IgniteModel<Matrix,Matrix>, SmoothParametrized<MultilayerPerceptron>, Serializable
```
Class encapsulating logic of multilayer perceptron.

See Also:

Serialized Form

Field Summary

Fields
Modifier and Type	Field and Description
`protected MLPArchitecture`	`architecture` This MLP architecture.
`protected MultilayerPerceptron`	`below` MLP which is 'below' this MLP (i.e. below output goes to this MLP as input).
`protected List<MLPLayer>`	`layers` List containing layers parameters.

Constructor Summary

Constructors
Modifier	Constructor and Description
	`MultilayerPerceptron(MLPArchitecture arch)` Construct MLP from given architecture.
	`MultilayerPerceptron(MLPArchitecture arch, MLPInitializer initializer)` Construct MLP from given architecture and parameters initializer.
`protected`	`MultilayerPerceptron(MultilayerPerceptron above, MultilayerPerceptron below)` Create MLP from two MLPs: first stacked on second.

Method Summary

All Methods Instance Methods Concrete Methods Default Methods
Modifier and Type	Method and Description
`MultilayerPerceptron`	`add(MultilayerPerceptron above)` Create MLP where this MLP output is fed as input to added MLP.
`MLPArchitecture`	`architecture()` Get architecture of this MLP.
`protected int`	`belowLayersCount()` Count of layers in below MLP.
`double`	`bias(int layerIdx, int neuronIdx)` Get the bias of given neuron in given layer.
`Vector`	`biases(int layerIdx)` Get biases of layer with given index.
`MLPState`	`computeState(Matrix val)` Perform forward pass and return state of outputs of each layer.
`Vector`	`differentiateByParameters(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss, Matrix inputsBatch, Matrix truthBatch)` Compose function in the following way: feed output of this model as input to second argument to loss function.
`Matrix`	`forwardPass(Matrix val, MLPState state, boolean writeState)` Perform forward pass and if needed write state of outputs of each layer.
`boolean`	`hasBiases(int layerIdx)` Checks if layer with given index has biases.
`int`	`layersCount()` Get count of layers in this MLP.
`Vector`	`parameters()` Get parameters vector.
`int`	`parametersCount()` Get count of parameters of this model.
`protected Vector`	`paramsAsVector(List<MLPLayer> layersParams)` Flatten this MLP parameters as vector.
`Matrix`	`predict(Matrix val)` Makes a prediction for the given objects.
`MultilayerPerceptron`	`setBias(int layerIdx, int neuronIdx, double val)` Set the bias of given neuron in given layer.
`MultilayerPerceptron`	`setBiases(int layerIdx, Vector bias)` Sets the biases of layer with a given index.
`MultilayerPerceptron`	`setParameters(Vector vector)` Set parameters.
`MultilayerPerceptron`	`setWeight(int layerIdx, int fromNeuron, int toNeuron, double val)` Set the weight of neuron with given index in previous layer to neuron with given index in given layer.
`MultilayerPerceptron`	`setWeights(int layerIdx, Matrix weights)` Sets the weighs of layer with a given index.
`String`	`toString()`
`String`	`toString(boolean pretty)`
`double`	`weight(int layerIdx, int fromNeuron, int toNeuron)` Get the weight of neuron with given index in previous layer to neuron with given index in given layer.
`Matrix`	`weights(int layerIdx)` Get weights of layer with given index.
`default M`	`withParameters(Vector vector)` Return new model with given parameters vector.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.ignite.ml.IgniteModel
andBefore, andThen, andThen, close, combine

- Field Detail
  - architecture
```
protected MLPArchitecture architecture
```
    This MLP architecture.
  - layers
```
protected List<MLPLayer> layers
```
    List containing layers parameters.
  - below
```
protected MultilayerPerceptron below
```
    MLP which is 'below' this MLP (i.e. below output goes to this MLP as input).
- Constructor Detail
  - MultilayerPerceptron
```
public MultilayerPerceptron(MLPArchitecture arch,
                            MLPInitializer initializer)
```
    Construct MLP from given architecture and parameters initializer.
    
    Parameters:
    
    arch - Architecture.
    
    initializer - Parameters initializer.
  - MultilayerPerceptron
```
public MultilayerPerceptron(MLPArchitecture arch)
```
    Construct MLP from given architecture.
    
    Parameters:
    
    arch - Architecture.
  - MultilayerPerceptron
```
protected MultilayerPerceptron(MultilayerPerceptron above,
                               MultilayerPerceptron below)
```
    Create MLP from two MLPs: first stacked on second.
    
    Parameters:
    
    above - MLP to be above.
    
    below - MLP to be below.
- Method Detail
  - computeState
```
public MLPState computeState(Matrix val)
```
    Perform forward pass and return state of outputs of each layer.
    
    Parameters:
    
    val - Value to perform computation on.
    
    Returns:
    
    MLP state after computation.
  - forwardPass
```
public Matrix forwardPass(Matrix val,
                          MLPState state,
                          boolean writeState)
```
    Perform forward pass and if needed write state of outputs of each layer.
    
    Parameters:
    
    val - Value to perform computation on.
    
    state - State object to write state into.
    
    writeState - Flag indicating need to write state.
  - predict
```
public Matrix predict(Matrix val)
```
    Makes a prediction for the given objects.
    
    Specified by:
    
    predict in interface Model<Matrix,Matrix>
    
    Parameters:
    
    val - Matrix containing objects.
    
    Returns:
    
    Matrix with predicted vectors.
  - add
```
public MultilayerPerceptron add(MultilayerPerceptron above)
```
    Create MLP where this MLP output is fed as input to added MLP.
    
    Parameters:
    
    above - Added MLP.
    
    Returns:
    
    New MLP where this MLP output is fed as input to added MLP.
  - weights
```
public Matrix weights(int layerIdx)
```
    Get weights of layer with given index. Proper indexes are in [1, layersCount).
    
    Parameters:
    
    layerIdx - Layer index.
    
    Returns:
    
    Weights of layer with given index.
  - biases
```
public Vector biases(int layerIdx)
```
    Get biases of layer with given index. Proper indexes are in [1, layersCount).
    
    Parameters:
    
    layerIdx - Layer index.
    
    Returns:
    
    Biases of layer with given index.
  - hasBiases
```
public boolean hasBiases(int layerIdx)
```
    Checks if layer with given index has biases.
    
    Parameters:
    
    layerIdx - Layer index.
    
    Returns:
    
    Value of predicate 'layer with layerIdx has biases'.
  - setBiases
```
public MultilayerPerceptron setBiases(int layerIdx,
                                      Vector bias)
```
    Sets the biases of layer with a given index.
    
    Parameters:
    
    layerIdx - Layer index.
    
    bias - New values for biases.
    
    Returns:
    
    This MLP with updated biases.
  - setBias
```
public MultilayerPerceptron setBias(int layerIdx,
                                    int neuronIdx,
                                    double val)
```
    Set the bias of given neuron in given layer.
    
    Parameters:
    
    layerIdx - Layer index.
    
    neuronIdx - Neuron index.
    
    val - New value of bias.
    
    Returns:
    
    This MLP with updated biases.
  - bias
```
public double bias(int layerIdx,
                   int neuronIdx)
```
    Get the bias of given neuron in given layer.
    
    Parameters:
    
    layerIdx - Layer index.
    
    neuronIdx - Neuron index.
    
    Returns:
    
    Bias with specified coordinates.
  - setWeights
```
public MultilayerPerceptron setWeights(int layerIdx,
                                       Matrix weights)
```
    Sets the weighs of layer with a given index.
    
    Parameters:
    
    layerIdx - Layer index.
    
    weights - New values for weights.
    
    Returns:
    
    This MLP with updated weights.
  - setWeight
```
public MultilayerPerceptron setWeight(int layerIdx,
                                      int fromNeuron,
                                      int toNeuron,
                                      double val)
```
    Set the weight of neuron with given index in previous layer to neuron with given index in given layer.
    
    Parameters:
    
    layerIdx - Layer index.
    
    fromNeuron - Neuron index in previous layer.
    
    toNeuron - Neuron index in current layer.
    
    val - New value of weight.
    
    Returns:
    
    This MLP with updated weights.
  - weight
```
public double weight(int layerIdx,
                     int fromNeuron,
                     int toNeuron)
```
    Get the weight of neuron with given index in previous layer to neuron with given index in given layer.
    
    Parameters:
    
    layerIdx - Layer index.
    
    fromNeuron - Neuron index in previous layer.
    
    toNeuron - Neuron index in current layer.
    
    Returns:
    
    Weight with specified coordinates.
  - layersCount
```
public int layersCount()
```
    Get count of layers in this MLP.
    
    Returns:
    
    Count of layers in this MLP.
  - belowLayersCount
```
protected int belowLayersCount()
```
    Count of layers in below MLP.
  - architecture
```
public MLPArchitecture architecture()
```
    Get architecture of this MLP.
    
    Returns:
    
    Architecture of this MLP.
  - differentiateByParameters
```
public Vector differentiateByParameters(IgniteFunction<Vector,IgniteDifferentiableVectorToDoubleFunction> loss,
                                        Matrix inputsBatch,
                                        Matrix truthBatch)
```
    Compose function in the following way: feed output of this model as input to second argument to loss function. After that we have a function g of three arguments: input, ground truth, parameters. If we consider function h(w) = 1 / M sum_{i=1}^{M} g(w, input_i, groundTruth_i), where M is number of entries in batch, we get function of one argument: parameters vector w. This function is being differentiated.
    
    Specified by:
    
    differentiateByParameters in interface SmoothParametrized<MultilayerPerceptron>
    
    Parameters:
    
    loss - Loss function.
    
    inputsBatch - Batch of inputs.
    
    truthBatch - Batch of ground truths.
    
    Returns:
    
    Gradient of h at current point in parameters space.
  - parameters
```
public Vector parameters()
```
    Get parameters vector.
    
    Returns:
    
    Parameters vector.
  - paramsAsVector
```
protected Vector paramsAsVector(List<MLPLayer> layersParams)
```
    Flatten this MLP parameters as vector.
    
    Parameters:
    
    layersParams - List of layers parameters.
    
    Returns:
    
    This MLP parameters as vector.
  - setParameters
```
public MultilayerPerceptron setParameters(Vector vector)
```
    Set parameters.
    
    Parameters:
    
    vector - Parameters vector.
  - parametersCount
```
public int parametersCount()
```
    Get count of parameters of this model.
    
    Returns:
    
    Count of parameters of this model.
  - toString
```
public String toString()
```
    Overrides:
    
    toString in class Object
  - toString
```
public String toString(boolean pretty)
```
    Specified by:
    
    toString in interface IgniteModel<Matrix,Matrix>
    
    Parameters:
    
    pretty - Use pretty mode.
  - withParameters
```
public M withParameters(Vector vector)
```
    Return new model with given parameters vector.
    
    Parameters:
    
    vector - Parameters vector.

Class MultilayerPerceptron

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Methods inherited from interface org.apache.ignite.ml.IgniteModel

Field Detail

architecture

layers

below

Constructor Detail

MultilayerPerceptron

MultilayerPerceptron

MultilayerPerceptron

Method Detail

computeState

forwardPass

predict

add

weights

biases

hasBiases

setBiases

setBias

bias

setWeights

setWeight

weight

layersCount

belowLayersCount

architecture

differentiateByParameters

parameters

paramsAsVector

setParameters

parametersCount

toString

toString

withParameters