fixed a typo (#240)

9bow · chsasank · commit 2d440315ad20 · 2018-05-15T09:30:53.000+05:30
diff --git a/beginner_source/former_torchies/autograd_tutorial.py b/beginner_source/former_torchies/autograd_tutorial.py
@@ -14,7 +14,7 @@
 
 In autograd, if any input ``Tensor`` of an operation has ``requires_grad=True``,
 the computation will be tracked. After computing the backward pass, a gradient
-w.r.t. this variable is accumulated into ``.grad`` attribute.
+w.r.t. this tensor is accumulated into ``.grad`` attribute.
 
 There’s one more class which is very important for autograd
 implementation - a ``Function``. ``Tensor`` and ``Function`` are
