diff --git a/README.md b/README.md
index a03d61b44bc7337fe29cfbb37d9b828ce62c2c94..a77e7adb7db1701d4a443811f714adef0ec99d0e 100644
--- a/README.md
+++ b/README.md
@@ -139,18 +139,6 @@ model.fit(train_dataset=trainset, test_dataset=testset, val_dataset=None)
 ```
 
 
-## Naming conventions
-
-Some naming conventions used in the code differ from the ones used in the paper:
-- CSNN: feature extraction layer
-- CSNN-1: CSNN-16 (16 feature maps)
-- CSNN-2: CSNN-64 (64 feature maps)
-- CSNN-3: CSNN-128 (128 feature maps)
-- Readout: classification layer
-- SSTDP-OG: SSTDPv1
-- SSTDP: SSTDPv2
-- PCN-SSTDP: SSTDPv2+PCN
-
 ## Known bugs
 
 - Depending on your machine, results on CIFAR-10 can slightly differ (not a significative difference though). It comes from the download/conversion process in `datasets/get_cifar10.py`.