Encog Top Commands :
Encog Top Commands : Source Chat GPT and Inspired from Arizona State University SGR 594 Machine Learning for Software Engineering
Encog machine learning framework, it’s a Java and .NET-based library developed by Jeff Heaton, designed for building and training neural networks. Encog supports various machine learning models, including neural networks, support vector machines, and genetic algorithms. It’s particularly noted for its educational value and is cited in numerous academic papers.
1. Simple XOR Neural Network
A basic example of training a neural network to solve the XOR problem using Encog’s
ResilientPropagation algorithm
import org.encog.Encog;
import org.encog.engine.network.activation.ActivationReLU;
import org.encog.engine.network.activation.ActivationSigmoid;
import org.encog.ml.data.MLData;
import org.encog.ml.data.MLDataSet;
import org.encog.ml.data.basic.BasicMLDataSet;
import org.encog.neural.networks.BasicNetwork;
import org.encog.neural.networks.layers.BasicLayer;
import org.encog.neural.networks.training.propagation.resilient.ResilientPropagation;
public class XORExample {
public static void main(String[] args) {
double[][] XOR_INPUT = { {0.0, 0.0}, {1.0, 0.0}, {0.0, 1.0}, {1.0, 1.0} };
double[][] XOR_IDEAL = { {0.0}, {1.0}, {1.0}, {0.0} };
BasicNetwork network = new BasicNetwork();
network.addLayer(new BasicLayer(null, true, 2));
network.addLayer(new BasicLayer(new ActivationReLU(), true, 5));
network.addLayer(new BasicLayer(new ActivationSigmoid(), false, 1));
network.getStructure().finalizeStructure();
network.reset();
MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
ResilientPropagation train = new ResilientPropagation(network, trainingSet);
int epoch = 1;
do {
train.iteration();
System.out.println(“Epoch #” + epoch + “ Error:” + train.getError());
epoch++;
} while (train.getError() > 0.01);
train.finishTraining();
System.out.println(“Neural Network Results:”);
for (MLData pair : trainingSet) {
MLData output = network.compute(pair.getInput());
System.out.println(pair.getInput().getData(0) + “,” + pair.getInput().getData(1)
+ “, actual=” + output.getData(0) + “, ideal=” + pair.getIdeal().getData(0));
}
Encog.getInstance().shutdown();
}
}
2. NEAT (NeuroEvolution of Augmenting Topologies) for XOR
Utilizes Encog’s NEAT implementation to evolve neural network topologies for solving the XOR problem.
import org.encog.ml.data.MLData;
import org.encog.ml.data.MLDataSet;
import org.encog.ml.data.basic.BasicMLDataSet;
import org.encog.neural.neat.NEATNetwork;
import org.encog.neural.neat.training.NEATPopulation;
import org.encog.neural.neat.training.NEATTrainer;
public class XORNEAT {
public static void main(String[] args) {
double[][] XOR_INPUT = { {0.0, 0.0}, {1.0, 0.0}, {0.0, 1.0}, {1.0, 1.0} };
double[][] XOR_IDEAL = { {0.0}, {1.0}, {1.0}, {0.0} };
MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
NEATPopulation population = new NEATPopulation(2, 1, 100);
NEATTrainer trainer = new NEATTrainer(population, trainingSet);
int epoch = 1;
do {
trainer.iteration();
System.out.println(“Epoch #” + epoch + “ Error:” + trainer.getError());
epoch++;
} while (trainer.getError() > 0.01);
trainer.finishTraining();
System.out.println(“Best network:”);
NEATNetwork best = trainer.getBestNetwork();
for (MLData pair : trainingSet) {
MLData output = best.compute(pair.getInput());
System.out.println(pair.getInput().getData(0) + “,” + pair.getInput().getData(1)
+ “, actual=” + output.getData(0) + “, ideal=” + pair.getIdeal().getData(0));
}
}
}
contact for Business in Delhi and India
Analytics, Mathematics Training.
Business consulting.
English and Education Consulting.
Subject to Availability:
shankytyagi.github.io
shankyedtech23@gmail.com
SHAAN TYAGI EDUCATION AND ANALYTICS ENTERPRISES Delhi : WEBSITE :
https://shaantyagi202.renderforestsites.com/
https://29785863-1455490.renderforestsites.com/
shankytyagi.github.io
