diff --git a/README.md b/README.md
index 514c68ee37b9888377d2a2e7382b8ba8c0a02f79..69ca44265021726dbe8437a446474a055ec4ac52 100644
--- a/README.md
+++ b/README.md
@@ -177,9 +177,7 @@ We also need that the last activation layer of the network to be a softmax layer
       - `labels_train` a vector of size `batch_size`, and
       - `learning_rate` the learning rate,
 
-    that perform one gradient descent step using a binary cross-entropy loss.
-    We admit that $`\frac{\partial C}{\partial Z^{(2)}} = A^{(2)} - Y`$, where $`Y`$ is a one-hot vector encoding the label.
-    The function must return:
+    that perform one gradient descent step using a binary cross-entropy loss. We admit that $`\frac{\partial C}{\partial Z^{(2)}} = A^{(2)} - Y`$, where $`Y`$ is a one-hot vector encoding the label. The function must return:
       - `w1`, `b1`, `w2` and `b2` the updated weights and biases of the network,
       - `loss` the loss, for monitoring purpose.
 13. Write the function `train_mlp` taking as parameters: