diff --git a/deeplearning4j/pom.xml b/deeplearning4j/pom.xml
index 9a381c6967..a8663865e0 100644
--- a/deeplearning4j/pom.xml
+++ b/deeplearning4j/pom.xml
@@ -48,7 +48,7 @@
     </dependencies>
 
     <properties>
-        <dl4j.version>1.0.0-beta5</dl4j.version>
+        <dl4j.version>0.9.1</dl4j.version> <!-- Latest non beta version -->
     </properties>
 
 </project>
diff --git a/deeplearning4j/src/main/java/com/baeldung/deeplearning4j/IrisClassifier.java b/deeplearning4j/src/main/java/com/baeldung/deeplearning4j/IrisClassifier.java
index b9c794650e..dcc81eda6e 100644
--- a/deeplearning4j/src/main/java/com/baeldung/deeplearning4j/IrisClassifier.java
+++ b/deeplearning4j/src/main/java/com/baeldung/deeplearning4j/IrisClassifier.java
@@ -4,6 +4,7 @@ import org.datavec.api.records.reader.RecordReader;
 import org.datavec.api.records.reader.impl.csv.CSVRecordReader;
 import org.datavec.api.split.FileSplit;
 import org.deeplearning4j.datasets.datavec.RecordReaderDataSetIterator;
+import org.deeplearning4j.eval.Evaluation;
 import org.deeplearning4j.nn.conf.BackpropType;
 import org.deeplearning4j.nn.conf.MultiLayerConfiguration;
 import org.deeplearning4j.nn.conf.NeuralNetConfiguration;
@@ -11,8 +12,6 @@ import org.deeplearning4j.nn.conf.layers.DenseLayer;
 import org.deeplearning4j.nn.conf.layers.OutputLayer;
 import org.deeplearning4j.nn.multilayer.MultiLayerNetwork;
 import org.deeplearning4j.nn.weights.WeightInit;
-import org.deeplearning4j.util.NetworkUtils;
-import org.nd4j.evaluation.classification.Evaluation;
 import org.nd4j.linalg.activations.Activation;
 import org.nd4j.linalg.api.ndarray.INDArray;
 import org.nd4j.linalg.dataset.DataSet;
@@ -51,11 +50,11 @@ public class IrisClassifier {
         DataSet testData = testAndTrain.getTest();
 
         MultiLayerConfiguration configuration = new NeuralNetConfiguration.Builder()
-                .maxNumLineSearchIterations(1000)
+                .iterations(1000)
                 .activation(Activation.TANH)
                 .weightInit(WeightInit.XAVIER)
-                //.regularization(true)
-                .l2(0.0001)
+                .regularization(true)
+                .learningRate(0.1).l2(0.0001)
                 .list()
                 .layer(0, new DenseLayer.Builder().nIn(FEATURES_COUNT).nOut(3)
                         .build())
@@ -64,12 +63,11 @@ public class IrisClassifier {
                 .layer(2, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD)
                         .activation(Activation.SOFTMAX)
                         .nIn(3).nOut(CLASSES_COUNT).build())
-                .backpropType(BackpropType.Standard)//.pretrain(false)
+                .backpropType(BackpropType.Standard).pretrain(false)
                 .build();
 
         MultiLayerNetwork model = new MultiLayerNetwork(configuration);
         model.init();
-        NetworkUtils.setLearningRate(model, 0.1);
         model.fit(trainingData);
 
         INDArray output = model.output(testData.getFeatures());
diff --git a/deeplearning4j/src/main/java/com/baeldung/logreg/MnistClassifier.java b/deeplearning4j/src/main/java/com/baeldung/logreg/MnistClassifier.java
index e320c366bf..ae705ffad7 100644
--- a/deeplearning4j/src/main/java/com/baeldung/logreg/MnistClassifier.java
+++ b/deeplearning4j/src/main/java/com/baeldung/logreg/MnistClassifier.java
@@ -10,6 +10,7 @@ import org.datavec.api.split.FileSplit;
 import org.datavec.image.loader.NativeImageLoader;
 import org.datavec.image.recordreader.ImageRecordReader;
 import org.deeplearning4j.datasets.datavec.RecordReaderDataSetIterator;
+import org.deeplearning4j.eval.Evaluation;
 import org.deeplearning4j.nn.conf.MultiLayerConfiguration;
 import org.deeplearning4j.nn.conf.NeuralNetConfiguration;
 import org.deeplearning4j.nn.conf.inputs.InputType;
@@ -21,15 +22,12 @@ import org.deeplearning4j.nn.multilayer.MultiLayerNetwork;
 import org.deeplearning4j.nn.weights.WeightInit;
 import org.deeplearning4j.optimize.listeners.ScoreIterationListener;
 import org.deeplearning4j.util.ModelSerializer;
-import org.nd4j.evaluation.classification.Evaluation;
 import org.nd4j.linalg.activations.Activation;
 import org.nd4j.linalg.dataset.api.iterator.DataSetIterator;
 import org.nd4j.linalg.dataset.api.preprocessor.DataNormalization;
 import org.nd4j.linalg.dataset.api.preprocessor.ImagePreProcessingScaler;
 import org.nd4j.linalg.learning.config.Nesterovs;
 import org.nd4j.linalg.lossfunctions.LossFunctions;
-import org.nd4j.linalg.schedule.MapSchedule;
-import org.nd4j.linalg.schedule.ScheduleType;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
@@ -71,8 +69,7 @@ public class MnistClassifier {
             String localFilePath = basePath + "mnist_png.tar.gz";
             File file = new File(localFilePath);
             if (!file.exists()) {
-                file.getParentFile()
-                    .mkdirs();
+                file.getParentFile().mkdirs();
                 Utils.downloadAndSave(dataUrl, file);
                 Utils.extractTarArchive(file, basePath);
             }
@@ -135,15 +132,15 @@ public class MnistClassifier {
             .build();
         final MultiLayerConfiguration config = new NeuralNetConfiguration.Builder().seed(seed)
             .l2(0.0005) // ridge regression value
-            .updater(new Nesterovs(new MapSchedule(ScheduleType.ITERATION, learningRateSchedule)))
+            .updater(new Nesterovs()) //TODO new MapSchedule(ScheduleType.ITERATION, learningRateSchedule)
             .weightInit(WeightInit.XAVIER)
             .list()
-            .layer(layer1)
-            .layer(layer2)
-            .layer(layer3)
-            .layer(layer2)
-            .layer(layer4)
-            .layer(layer5)
+            .layer(0, layer1)
+            .layer(1, layer2)
+            .layer(2, layer3)
+            .layer(3, layer2)
+            .layer(4, layer4)
+            .layer(5, layer5)
             .setInputType(InputType.convolutionalFlat(height, width, channels))
             .build();