Update neural_networks_tutorial.py

Author: soumith

beginner_source/blitz/neural_networks_tutorial.py

@@ -30,7 +30,7 @@
 - Compute the loss (how far is the output from being correct)
 - Propagate gradients back into the network’s parameters
 - Update the weights of the network, typically using a simple update rule:
-  ``weight = weight + learning_rate * gradient``
+  ``weight = weight - learning_rate * gradient``
 
 Define the network
 ------------------