beginner/blitz/nn: Fix misleading typo on which term to be differentiated against (#726)

rht · holly1238 · web-flow · commit ff0cfa18e1df · 2021-04-25T13:01:43.000-07:00
Co-authored-by: holly1238 &lt;77758406+holly1238@users.noreply.github.com&gt;
diff --git a/beginner_source/blitz/neural_networks_tutorial.py b/beginner_source/blitz/neural_networks_tutorial.py
@@ -176,8 +176,9 @@ def num_flat_features(self, x):
 #           -> loss
 #
 # So, when we call ``loss.backward()``, the whole graph is differentiated
-# w.r.t. the loss, and all Tensors in the graph that have ``requires_grad=True``
-# will have their ``.grad`` Tensor accumulated with the gradient.
+# w.r.t. the neural net parameters, and all Tensors in the graph that have
+# ``requires_grad=True`` will have their ``.grad`` Tensor accumulated with the
+# gradient.
 #
 # For illustration, let us follow a few steps backward:
 

Original file line number	Diff line number	Diff line change
`@@ -176,8 +176,9 @@ def num_flat_features(self, x):`
`176`	`176`	`# -> loss`
`177`	`177`	`#`
`178`	`178`	# So, when we call ``loss.backward()``, the whole graph is differentiated
`179`		-# w.r.t. the loss, and all Tensors in the graph that have ``requires_grad=True``
`180`		-# will have their ``.grad`` Tensor accumulated with the gradient.
	`179`	`+# w.r.t. the neural net parameters, and all Tensors in the graph that have`
	`180`	+# ``requires_grad=True`` will have their ``.grad`` Tensor accumulated with the
	`181`	`+# gradient.`
`181`	`182`	`#`
`182`	`183`	`# For illustration, let us follow a few steps backward:`
`183`	`184`