diff --git a/README.md b/README.md
index 0610810..1db8963 100644
--- a/README.md
+++ b/README.md
@@ -144,7 +144,7 @@ R2Score(trained, test) should be > 0.8f
     - Add state between batches
     - Try LSTM weights fusing (x4 less weights)
 - [ ] Layers Dropout (provide random generator to layers)(Wanted!)
-- [ ] Batch Normalization (Wanted!)
+- [x] Batch Normalization
 - [ ] others
 
 # Localization & Object Detection & Instance Segmentation
diff --git a/TODO.md b/TODO.md
index 903fec3..e69de29 100644
--- a/TODO.md
+++ b/TODO.md
@@ -1,4 +0,0 @@
-- Lift optimizer inside a function with params
-- Expose params in LossModel, TrainedModel
-- Check if needs farther refactoring
-- Batch Norm
\ No newline at end of file