org.apache.ignite.ml.optimization

Interface SmoothParametrized<M extends Parametrized<M>>

All Superinterfaces:

AutoCloseable, IgniteModel<Matrix,Matrix>, Model<Matrix,Matrix>, Parametrized<M>, Serializable

All Known Implementing Classes:

MultilayerPerceptron

public interface SmoothParametrized<M extends Parametrized<M>>
extends Parametrized<M>, IgniteModel<Matrix,Matrix>

Interface for models which are smooth functions of their parameters.

Method Summary

Modifier and Type	Method and Description
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.
Vector	parameters() Get parameters vector.
int	parametersCount() Get count of parameters of this model.
M	setParameters(Vector vector) Set parameters.
default M	withParameters(Vector vector) Return new model with given parameters vector.

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

andBefore, andThen, andThen, close, combine, toString

Methods inherited from interface org.apache.ignite.ml.inference.Model

predict

Method Detail

differentiateByParameters

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.

Parameters:

loss - Loss function.

inputsBatch - Batch of inputs.

truthBatch - Batch of ground truths.

Returns:

Gradient of h at current point in parameters space.

parameters

Vector parameters()

Get parameters vector.

Returns:

Parameters vector.

setParameters

M setParameters(Vector vector)

Set parameters.

Parameters:

vector - Parameters vector.

withParameters

default M withParameters(Vector vector)

Return new model with given parameters vector.

Parameters:

vector - Parameters vector.

parametersCount

int parametersCount()

Get count of parameters of this model.

Returns:

Count of parameters of this model.