diff --git a/README.md b/README.md
index d8b88d8272a71efd78b49c497eb53cbfd7e3f584..c1a77a9434fabba0c30037d363b5c5f173abda07 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,7 @@ The MNIST database of handwritten digits, available from this [link](http://yann
 
 ## Open Binary MNIST notebook:
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1RVtgS6NOH5D5ssa19qDt35DYnjPxJCOX)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)]()
 
 ## Results on MNIST:
 
@@ -66,7 +66,7 @@ The Omniglot data set is designed for developing more human-like learning algori
 
 ## Open Binary Omniglot notebook:
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1z7ebfh8VWKfgkecpRzY7iiM6NT2ElWBL)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)]()
 
 ## Results on Omniglot classification with data train (80% train, 10% validation and 10% test):
 ### Loss/ACC: with 10 epochs.
@@ -92,7 +92,7 @@ In this part, we present results obtained with [Matching Networks for One Shot L
 
 ## Open binary few shot Omniglot notebook:
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1GW_yLVN62nRDgQrPAUkeM1b7yGSGSWg5)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)]()
 
 ## Results on Omniglot few shot learning:
 ### ACC: with this repository with 10 epochs.