diff --git a/docs/machine-learning/neural-network/multilayer-perceptron-classifier.md b/docs/machine-learning/neural-network/multilayer-perceptron-classifier.md
index d2f746d..a6b060a 100644
--- a/docs/machine-learning/neural-network/multilayer-perceptron-classifier.md
+++ b/docs/machine-learning/neural-network/multilayer-perceptron-classifier.md
@@ -8,7 +8,7 @@ A multilayer perceptron (MLP) is a feedforward artificial neural network model t
 * $hiddenLayers (array) - array with the hidden layers configuration, each value represent number of neurons in each layers
 * $classes (array) - array with the different training set classes (array keys are ignored)
 * $iterations (int) - number of training iterations
-* $theta (int) - network theta parameter
+* $learningRate (float) - the learning rate
 * $activationFunction (ActivationFunction) - neuron activation function
 
 ```
diff --git a/src/Phpml/NeuralNetwork/Network/MultilayerPerceptron.php b/src/Phpml/NeuralNetwork/Network/MultilayerPerceptron.php
index 9ef3f73..94a8423 100644
--- a/src/Phpml/NeuralNetwork/Network/MultilayerPerceptron.php
+++ b/src/Phpml/NeuralNetwork/Network/MultilayerPerceptron.php
@@ -46,9 +46,9 @@ abstract class MultilayerPerceptron extends LayeredNetwork implements Estimator,
     protected $activationFunction;
 
     /**
-     * @var int
+     * @var float
      */
-    private $theta;
+    private $learningRate;
 
     /**
      * @var Backpropagation
@@ -58,7 +58,7 @@ abstract class MultilayerPerceptron extends LayeredNetwork implements Estimator,
     /**
      * @throws InvalidArgumentException
      */
-    public function __construct(int $inputLayerFeatures, array $hiddenLayers, array $classes, int $iterations = 10000, ?ActivationFunction $activationFunction = null, int $theta = 1)
+    public function __construct(int $inputLayerFeatures, array $hiddenLayers, array $classes, int $iterations = 10000, ?ActivationFunction $activationFunction = null, float $learningRate = 1)
     {
         if (empty($hiddenLayers)) {
             throw InvalidArgumentException::invalidLayersNumber();
@@ -73,7 +73,7 @@ abstract class MultilayerPerceptron extends LayeredNetwork implements Estimator,
         $this->inputLayerFeatures = $inputLayerFeatures;
         $this->hiddenLayers = $hiddenLayers;
         $this->activationFunction = $activationFunction;
-        $this->theta = $theta;
+        $this->learningRate = $learningRate;
 
         $this->initNetwork();
     }
@@ -87,7 +87,7 @@ abstract class MultilayerPerceptron extends LayeredNetwork implements Estimator,
         $this->addBiasNodes();
         $this->generateSynapses();
 
-        $this->backpropagation = new Backpropagation($this->theta);
+        $this->backpropagation = new Backpropagation($this->learningRate);
     }
 
     public function train(array $samples, array $targets): void
diff --git a/src/Phpml/NeuralNetwork/Training/Backpropagation.php b/src/Phpml/NeuralNetwork/Training/Backpropagation.php
index 98683ab..6722bd1 100644
--- a/src/Phpml/NeuralNetwork/Training/Backpropagation.php
+++ b/src/Phpml/NeuralNetwork/Training/Backpropagation.php
@@ -10,9 +10,9 @@ use Phpml\NeuralNetwork\Training\Backpropagation\Sigma;
 class Backpropagation
 {
     /**
-     * @var int
+     * @var float
      */
-    private $theta;
+    private $learningRate;
 
     /**
      * @var array
@@ -24,9 +24,9 @@ class Backpropagation
      */
     private $prevSigmas = null;
 
-    public function __construct(int $theta)
+    public function __construct(float $learningRate)
     {
-        $this->theta = $theta;
+        $this->learningRate = $learningRate;
     }
 
     /**
@@ -43,7 +43,7 @@ class Backpropagation
                 if ($neuron instanceof Neuron) {
                     $sigma = $this->getSigma($neuron, $targetClass, $key, $i == $layersNumber);
                     foreach ($neuron->getSynapses() as $synapse) {
-                        $synapse->changeWeight($this->theta * $sigma * $synapse->getNode()->getOutput());
+                        $synapse->changeWeight($this->learningRate * $sigma * $synapse->getNode()->getOutput());
                     }
                 }
             }