diff --git a/README.md b/README.md
index 98ed780dad0fb41ea7e9bdc1186e31accc5ce874..4e44d755191f56d6cfd4889c3afd00c851e6e1d3 100644
--- a/README.md
+++ b/README.md
@@ -120,6 +120,7 @@ They generate dummy data, where one can set different parameters.
     - [regression loss](https://datamonje.com/regression-loss-functions/)
     - [regularization](http://www.chioka.in/differences-between-l1-and-l2-as-loss-function-and-regularization/)
     - [activation functions](https://towardsdatascience.com/creating-neural-networks-from-scratch-in-python-6f02b5dd911)
+    - [hopfield layer](https://ml-jku.github.io/hopfield-layers/)
     - [rnn - theory](https://www.freecodecamp.org/news/the-ultimate-guide-to-recurrent-neural-networks-in-python/)
     - [rnn - implementation](https://towardsdatascience.com/recurrent-neural-networks-rnns-3f06d7653a85)
     - [rnn - implementation](https://medium.com/@VersuS_/coding-a-recurrent-neural-network-rnn-from-scratch-using-pytorch-a6c9fc8ed4a7)