Package edu.cmu.tetrad.search.utils

Class MultiLayerPerceptronFunction1D

java.lang.Object

edu.cmu.tetrad.search.utils.MultiLayerPerceptronFunction1D

public class MultiLayerPerceptronFunction1D
extends Object

This class implements a 1-dimensional Multi-Layer Perceptron (MLP) function. It consists of a single hidden layer and scales the input to introduce variability or "bumpiness" as needed. The activation function for the hidden layer and weights/biases for the neural network are initialized during construction.

Constructor Summary

Constructors

Constructor	Description
MultiLayerPerceptronFunction1D(int hiddenDimension, double inputScale, Function<Double,Double> activation, long seed)	Constructor to initialize a random function.

Method Summary

Modifier and Type	Method	Description
double	evaluate(double x)	Evaluates the random function for a given input.
static void	main(String[] args)	The entry point of the application that demonstrates the usage of the MultiLayerPerceptronFunction1D class by defining a random function with specific parameters and evaluating it over a range of inputs.

Methods inherited from class java.lang.Object

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

Constructor Details

MultiLayerPerceptronFunction1D

public MultiLayerPerceptronFunction1D(int hiddenDimension,
 double inputScale,
 Function<Double,Double> activation,
 long seed)

Constructor to initialize a random function.

Parameters:

hiddenDimension - Number of neurons in the hidden layer.

inputScale - Scaling factor for the input to create bumpiness.

activation - Activation function (e.g., Math::sin or Math::tanh).

seed - Random seed for reproducibility.

Method Details

main

public static void main(String[] args)

The entry point of the application that demonstrates the usage of the MultiLayerPerceptronFunction1D class by defining a random function with specific parameters and evaluating it over a range of inputs.

Parameters:

args - Command-line arguments passed to the program.

evaluate

public double evaluate(double x)

Evaluates the random function for a given input.

Parameters:

x - Input value in R.

Returns:

Output value in R.