diff --git a/Source/MainComponent.cpp b/Source/MainComponent.cpp
index c11825f..4cb0e62 100644
--- a/Source/MainComponent.cpp
+++ b/Source/MainComponent.cpp
@@ -278,8 +278,8 @@ MainComponent::MainComponent ()
     rbmDoSampleBatch->addListener (this);
 
     addAndMakeVisible (sizeMiniBatch = new Label ("sizeMiniBatch",
-                                                  TRANS("0")));
-    sizeMiniBatch->setTooltip (TRANS("Maximum number of training samples per train"));
+                                                  TRANS("100")));
+    sizeMiniBatch->setTooltip (TRANS("Mini batch size"));
     sizeMiniBatch->setFont (Font (15.00f, Font::plain));
     sizeMiniBatch->setJustificationType (Justification::centred);
     sizeMiniBatch->setEditable (true, true, false);
@@ -724,7 +724,6 @@ void MainComponent::labelTextChanged (Label* labelThatHasChanged)
     else if (labelThatHasChanged == sizeMiniBatch)
     {
         //[UserLabelCode_sizeMiniBatch] -- add your label text handling code here..
-		m_pRbmComponentCurr->setMiniBatchSize((size_t)labelThatHasChanged->getText().getFloatValue());
         //[/UserLabelCode_sizeMiniBatch]
     }
 
@@ -875,9 +874,7 @@ const juce::String& MainComponent::getBaseDir()
 
 void MainComponent::run()
 {
-//	trainButton->setEnabled(false);
-	m_pRbmComponentCurr->train(numEpochslabel->getText().getIntValue());
-//	trainButton->setEnabled(true);
+	m_pRbmComponentCurr->train((size_t)numEpochslabel->getText().getIntValue(), (size_t)sizeMiniBatch->getText().getIntValue());
 }
 
 void MainComponent::onChanged(const LayerArray &obj)
@@ -913,7 +910,6 @@ void MainComponent::updateControls()
 	numVisibleLabel->setText(String(m_weightsCurr->getNumVisibleX()), dontSendNotification );
 	numVisibleYLabel->setText(String(m_weightsCurr->getNumVisibleY()), dontSendNotification );
 	numHiddenLabel->setText(String(m_weightsCurr->getNumHidden()), dontSendNotification );
-	sizeMiniBatch->setText(String(m_pRbmComponentCurr->params().m_miniBatchSize), dontSendNotification);
 
 	WeightsSlider->setRange(0, m_weightsCurr->getNumHidden()-1, 1);
 	numGibbsSlider->setValue(m_pRbmComponentCurr->params().m_numGibbs);
@@ -1118,8 +1114,8 @@ BEGIN_JUCER_METADATA
                 buttonText="Sample training" connectedEdges="0" needsCallback="1"
                 radioGroupId="0" state="0"/>
   <LABEL name="sizeMiniBatch" id="dd9e3e6f2b7b22f8" memberName="sizeMiniBatch"
-         virtualName="" explicitFocusOrder="0" pos="1064 20 48 24" tooltip="Maximum number of training samples per train"
-         edTextCol="ff000000" edBkgCol="0" labelText="0" editableSingleClick="1"
+         virtualName="" explicitFocusOrder="0" pos="1064 20 48 24" tooltip="Mini batch size"
+         edTextCol="ff000000" edBkgCol="0" labelText="100" editableSingleClick="1"
          editableDoubleClick="1" focusDiscardsChanges="0" fontname="Default font"
          fontsize="15" bold="0" italic="0" justification="36"/>
   <TOGGLEBUTTON name="rbmUseHiddenGaussian toggle button" id="92e05c920283616b"
diff --git a/Source/Rbm.cpp b/Source/Rbm.cpp
index 3bf1d09..9627a26 100644
--- a/Source/Rbm.cpp
+++ b/Source/Rbm.cpp
@@ -17,7 +17,6 @@ Rbm::Rbm(Weights &weights, const MatrixXd &batch)
 , m_variableSigma(weights.getNumVisible())
 , m_progress(0)
 {
-	setMiniBatchSize(batch.rows());
 	Noise_Init(&m_noise, 0x32727155);
 	m_variableSigma.fill(m_params.m_constantSigma);
 	updateHiddenBatch();
@@ -198,17 +197,17 @@ MatrixXd Rbm::calcZ(MatrixXd &v, MatrixXd &h)
 	return t1;
 }
 
-void Rbm::train(uint32_t numEpochs, double sigmaMin)
+void Rbm::train(size_t numEpochs, size_t miniBatchSize, double sigmaMin)
 {
-	uint32_t i;
-	uint32_t epoch;
-	uint32_t gibbs;
+	size_t i;
+	size_t epoch;
+	size_t gibbs;
 
 	size_t trainingSize = m_batch.rows();
 	size_t trainingSizeRemain = trainingSize;
 	size_t batchRowIndex = 0;
 	
-	double dProgress = 1.0/(numEpochs*(double)trainingSize/std::min(m_params.m_miniBatchSize, trainingSize));
+	double dProgress = 1.0/(numEpochs*(double)trainingSize/std::min(miniBatchSize, trainingSize));
 
 	MatrixXd dBiasV_curr(MatrixXd::Zero(1, m_w.getNumVisible()));
 	MatrixXd dBiasH_curr(MatrixXd::Zero(1, m_w.getNumHidden()));
@@ -221,14 +220,14 @@ void Rbm::train(uint32_t numEpochs, double sigmaMin)
 	while (trainingSizeRemain)
 	{
 		cout << "trainingSizeRemain: " << trainingSizeRemain << endl;
-		size_t toSlice = std::min(m_params.m_miniBatchSize, trainingSizeRemain);
+		size_t toSlice = std::min(miniBatchSize, trainingSizeRemain);
 		MatrixXd batch = m_batch.block(batchRowIndex, 0, toSlice, m_w.getNumVisible());
 		trainingSizeRemain -= toSlice;
 		batchRowIndex += toSlice;
 		size_t batchSize = batch.rows();
-		double mu_w = m_params.m_muWeights/std::min(m_params.m_miniBatchSize, trainingSize);
-		double mu_biasV = m_params.m_muWeights/std::min(m_params.m_miniBatchSize, trainingSize);
-		double mu_biasH = m_params.m_muWeights/std::min(m_params.m_miniBatchSize, trainingSize);
+		double mu_w = m_params.m_muWeights/std::min(miniBatchSize, trainingSize);
+		double mu_biasV = m_params.m_muWeights/std::min(miniBatchSize, trainingSize);
+		double mu_biasH = m_params.m_muWeights/std::min(miniBatchSize, trainingSize);
 
 		MatrixXd batch_sampled(batchSize, m_w.getNumVisible());
 		MatrixXd v_sampled(batchSize, m_w.getNumVisible()); 
@@ -514,11 +513,6 @@ void Rbm::setNumGibbs(size_t value)
 	onParamsChanged();
 }
 
-void Rbm::setMiniBatchSize(size_t size)
-{
-	m_params.m_miniBatchSize = size;
-}
-
 void Rbm::setMuWeights(double value)
 {
 	m_params.m_muWeights = value;
diff --git a/Source/Rbm.hpp b/Source/Rbm.hpp
index 639996e..fcd23c7 100644
--- a/Source/Rbm.hpp
+++ b/Source/Rbm.hpp
@@ -37,7 +37,6 @@ public:
 		, m_doNormalizeData(false)
 		, m_doLearnVariance(false)
 		, m_numGibbs(1)
-		, m_miniBatchSize(100)
 		{
 		}
 		
@@ -58,7 +57,6 @@ public:
 		bool m_doNormalizeData;
 		bool m_doLearnVariance;
 		size_t m_numGibbs;
-		size_t m_miniBatchSize;
 	};
 	
 	Rbm(Weights &weights, const MatrixXd &batch);
@@ -78,7 +76,7 @@ public:
 	RowVectorXd calcMean(MatrixXd const &batch);
 	RowVectorXd calcSigma(MatrixXd const &batch);
 	MatrixXd calcZ(MatrixXd &v, MatrixXd &h);
-	void train(uint32_t numEpochs, double sigmaMin = 0.05);
+	void train(size_t numEpochs, size_t miniBatchSize, double sigmaMin = 0.05);
 	double getProgress() const;
 	double getEnergy(const VectorXd& visible, const VectorXd& hidden);
 	void toHidden(RowVectorXd &h, RowVectorXd const &v);
@@ -98,7 +96,6 @@ public:
 	void setNormalizeData(bool flag);
 	void setDoLearnVariance(bool flag);
 	void setNumGibbs(size_t value);
-	void setMiniBatchSize(size_t size);
 	void setMuWeights(double value);
 	void setMuSparsity(double value);
 	void setMomentum(double value);