fix link

README.md

@@ -92,7 +92,7 @@ and/or model averaging.
 Regarding **supervised** CKN model training (without data augmentation),
 the best results regarding prediction accuracy were achieved with a 14 layer
 CKN model. Details about the architectures that were used can be found
-[here](./ckn/tutorials/supervised_example.py).
+[here](./ckntf/tutorials/supervised_example.py).
 
 **NB:** The Matlab-based code was able to reach an accuracy of 90.5% with
 the 14 layer model on the pre-whitened Cifar10 data set. For unknow reasons