BAEL-771

libraries/README.md

@@ -26,6 +26,7 @@
 - [A Guide to Apache Commons DbUtils](http://www.baeldung.com/apache-commons-dbutils)
 - [Introduction to Awaitility](http://www.baeldung.com/awaitlity-testing)
 - [Guide to the HyperLogLog Algorithm](http://www.baeldung.com/java-hyperloglog)
+- [Introduction to Neuroph](http://www.baeldung.com/intro-to-neuroph)
 
 The libraries module contains examples related to small libraries that are relatively easy to use and does not require any separate module of its own.
 

libraries/pom.xml

@@ -7,7 +7,6 @@
         <version>1.0.0-SNAPSHOT</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
-
     <artifactId>libraries</artifactId>
     <name>libraries</name>
     <build>
@@ -71,9 +70,51 @@
                     </execution>
                 </executions>
             </plugin>
+             <!-- Neuroph -->
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-jar-plugin</artifactId>
+                <version>3.0.2</version>
+                <configuration>
+                    <excludes>
+                        <exclude>**/log4j.properties</exclude>
+                    </excludes>
+                    <archive>
+                        <manifest>
+                            <mainClass>com.baeldung.neuroph.NeurophXOR</mainClass>
+                        </manifest>
+                    </archive>
+                </configuration>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-surefire-plugin</artifactId>
+                <version>2.18.1</version>
+                <executions>
+                    <execution>
+                        <id>test</id>
+                        <phase>test</phase>
+                        <goals>
+                            <goal>test</goal>
+                        </goals>
+                        <configuration>
+                            <includes>
+                                <include>test/java/com/baeldung/neuroph/XORTest.java</include>
+                            </includes>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+            <!-- /Neuroph -->
         </plugins>
     </build>
     <dependencies>
+        <!-- https://mvnrepository.com/artifact/org.beykery/neuroph/2.92 -->
+        <dependency>
+            <groupId>org.beykery</groupId>
+            <artifactId>neuroph</artifactId>
+            <version>${neuroph.version}</version>
+        </dependency>
         <!-- https://mvnrepository.com/artifact/cglib/cglib -->
         <dependency>
             <groupId>cglib</groupId>
@@ -327,7 +368,6 @@
             <artifactId>quartz</artifactId>
             <version>2.3.0</version>
         </dependency>
-
         <dependency>
             <groupId>one.util</groupId>
             <artifactId>streamex</artifactId>
@@ -432,6 +472,7 @@
         <commons.io.version>2.5</commons.io.version>
         <flink.version>1.2.0</flink.version>
         <jackson.version>2.8.5</jackson.version>
+        <neuroph.version>2.92</neuroph.version>
         <serenity.version>1.4.0</serenity.version>
         <serenity.jbehave.version>1.24.0</serenity.jbehave.version>
         <serenity.jira.version>1.1.3-rc.5</serenity.jira.version>

libraries/src/main/java/com/baeldung/neuroph/NeurophXOR.java

@@ -0,0 +1,73 @@
+package com.baeldung.neuroph;
+
+import org.neuroph.core.Layer;
+import org.neuroph.core.NeuralNetwork;
+import org.neuroph.core.Neuron;
+import org.neuroph.core.data.DataSet;
+import org.neuroph.core.data.DataSetRow;
+import org.neuroph.nnet.learning.BackPropagation;
+import org.neuroph.util.ConnectionFactory;
+import org.neuroph.util.NeuralNetworkType;
+
+public class NeurophXOR {
+
+    public static NeuralNetwork assembleNeuralNetwork() {
+
+        Layer inputLayer = new Layer();
+        inputLayer.addNeuron(new Neuron());
+        inputLayer.addNeuron(new Neuron());
+
+        Layer hiddenLayerOne = new Layer();
+        hiddenLayerOne.addNeuron(new Neuron());
+        hiddenLayerOne.addNeuron(new Neuron());
+        hiddenLayerOne.addNeuron(new Neuron());
+        hiddenLayerOne.addNeuron(new Neuron());
+
+        Layer hiddenLayerTwo = new Layer();
+        hiddenLayerTwo.addNeuron(new Neuron());
+        hiddenLayerTwo.addNeuron(new Neuron());
+        hiddenLayerTwo.addNeuron(new Neuron());
+        hiddenLayerTwo.addNeuron(new Neuron());
+
+        Layer outputLayer = new Layer();
+        outputLayer.addNeuron(new Neuron());
+
+        NeuralNetwork ann = new NeuralNetwork();
+
+        ann.addLayer(0, inputLayer);
+        ann.addLayer(1, hiddenLayerOne);
+        ConnectionFactory.fullConnect(ann.getLayerAt(0), ann.getLayerAt(1));
+        ann.addLayer(2, hiddenLayerTwo);
+        ConnectionFactory.fullConnect(ann.getLayerAt(1), ann.getLayerAt(2));
+        ann.addLayer(3, outputLayer);
+        ConnectionFactory.fullConnect(ann.getLayerAt(2), ann.getLayerAt(3));
+        ConnectionFactory.fullConnect(ann.getLayerAt(0), ann.getLayerAt(ann.getLayersCount()-1), false);
+
+        ann.setInputNeurons(inputLayer.getNeurons());
+        ann.setOutputNeurons(outputLayer.getNeurons());
+
+        ann.setNetworkType(NeuralNetworkType.MULTI_LAYER_PERCEPTRON);
+        return ann;
+    }
+
+    public static NeuralNetwork trainNeuralNetwork(NeuralNetwork ann) {
+        int inputSize = 2;
+        int outputSize = 1;
+        DataSet ds = new DataSet(inputSize, outputSize);
+
+        DataSetRow rOne = new DataSetRow(new double[] {0, 1}, new double[] {1});
+        ds.addRow(rOne);
+        DataSetRow rTwo = new DataSetRow(new double[] {1, 1}, new double[] {0});
+        ds.addRow(rTwo);
+        DataSetRow rThree = new DataSetRow(new double[] {0, 0}, new double[] {0});
+        ds.addRow(rThree);
+        DataSetRow rFour = new DataSetRow(new double[] {1, 0}, new double[] {1});
+        ds.addRow(rFour);
+
+        BackPropagation backPropagation = new BackPropagation();
+        backPropagation.setMaxIterations(1000);
+
+        ann.learn(ds, backPropagation);
+        return ann;
+    }
+}

libraries/src/test/java/com/baeldung/neuroph/XORTest.java

@@ -0,0 +1,50 @@
+package com.baeldung.neuroph;
+
+import org.junit.After;
+import org.junit.Before;
+import org.junit.Test;
+import org.neuroph.core.NeuralNetwork;
+
+import static org.junit.Assert.*;
+
+public class XORTest {
+    private NeuralNetwork ann = null;
+
+    @Before
+    public void annInit() {
+        ann = NeurophXOR.trainNeuralNetwork(NeurophXOR.assembleNeuralNetwork());
+    }
+
+    @Test
+    public void leftDisjunctTest() {
+        ann.setInput(0, 1);
+        ann.calculate();
+        assertEquals(ann.getOutput()[0], 1.0,0.0);
+    }
+
+    @Test
+    public void rightDisjunctTest() {
+        ann.setInput(1, 0);
+        ann.calculate();
+        assertEquals(ann.getOutput()[0], 1.0,0.0);
+    }
+
+    @Test
+    public void bothFalseConjunctTest() {
+        ann.setInput(0, 0);
+        ann.calculate();
+        assertEquals(ann.getOutput()[0], 0.0,0.0);
+    }
+
+    @Test
+    public void bothTrueConjunctTest() {
+        ann.setInput(1, 1);
+        ann.calculate();
+        assertEquals(ann.getOutput()[0], 0.0,0.0);
+    }
+
+    @After
+    public void annClose() {
+        ann = null;
+    }
+}