diff --git a/Chapters/16-Energy-Based-Models/INDEX.md b/Chapters/16-Energy-Based-Models/INDEX.md
index 93e7de1..073e485 100644
--- a/Chapters/16-Energy-Based-Models/INDEX.md
+++ b/Chapters/16-Energy-Based-Models/INDEX.md
@@ -234,6 +234,9 @@ we would not widen the dissimilarity between positive and negative examples.[^at
 
 ## Self Supervised Learning
 
+It's a method of learning parts of data by other data parts. One example is BERT,
+or T5 that operates over Masked Language Tasks that involves predicting  pieces
+of missing text, by looking at the remaining data.
 
 
 <!--