fixed minor typos in gettingstarted.txt

Author: dallascard

doc/gettingstarted.txt

@@ -104,7 +104,7 @@ MNIST Dataset
  Since now the data is in one variable, and a minibatch is defined as a
  slice of that variable, it comes more natural to define a minibatch by
  indicating its index and its size. In our setup the batch size stays constant
- through out the execution of the code, therefore a function will actually
+ throughout the execution of the code, therefore a function will actually
  require only the index to identify on which datapoints to work.
  The code below shows how to store your data and how to
  access a minibatch:
@@ -141,8 +141,8 @@ MNIST Dataset
 
     # accessing the third minibatch of the training set
 
-    data  = train_set_x[2 * 500: 3 * 500]
-    label = train_set_y[2 * 500: 3 * 500]
+    data  = train_set_x[2 * batch_size: 3 * batch_size]
+    label = train_set_y[2 * batch_size: 3 * batch_size]
 
 
 The data has to be stored as floats on the GPU ( the right