diff --git a/README.md b/README.md
index 7065766..6eb6c53 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,5 @@
 # dnn_ensemble_ids
-DNN-Ensemble IDS is a machine learning based classification model for intrusion detection exploiting a Specialized Ensemble of classifiers. Multiple base classifiers are trained on data gathered in different time windows where different types of attacks occur (Data Chunks). These base classifiers take the form of Deep Neural Networks (DNNs) sharing all the same architecture, but trained against different samples of the given training data. Finally, an incremental learning schema is adopted to cope with different problems such as Large high-speed datastream and rare attacks.
+DNN-Ensemble IDS is a machine learning based classification model for intrusion detection exploiting ensembles of classifiers. Multiple base classifiers are trained on data gathered in different time windows where different types of attacks occur (Data Chunks). These base classifiers take the form of Deep Neural Networks (DNNs) sharing all the same architecture, but trained against different samples of the given training data. Finally, an incremental learning schema is adopted to cope with different problems such as Large high-speed datastream and rare attacks.
 
 ## Author
 
@@ -9,4 +9,4 @@ The code is developed and maintained by Massimo Guarascio and Gianluigi Folino (
 
 First, download this repo:
 - You need to have 'python' installed.
-- You also need to install 'numpy', 'matplotplib', 'pandas', and 'sklearn', 'mlxtend', 'keras' and 'tensorflow 1.4'.
+- You also need to install 'numpy', 'pandas==1.0.3', and 'sklearn <=0.21', 'mlxtend', 'Keras==2.2.4' and 'tensorflow==1.14.0'.