Some typos fixed - ( added coma to have 60,000 instead of 60 000 - this way the number is not broken into 60 on a line and 000 on the other; fixed intendention in code example)

Author: pascanur

doc/gettingstarted.txt

@@ -26,10 +26,10 @@ MNIST Dataset
 (`mnist.pkl.gz <http://deeplearning.net/data/mnist/mnist.pkl.gz>`_)
 
  The `MNIST <http://yann.lecun.com/exdb/mnist>`_ dataset consists of handwritten 
- digit images and it is divided in 60 000 examples for the training set and 
- 10 000 examples for testing. In many papers as well as in this tutorial, the
- official training set of 60 000 is divided into an actual training set of 50 000
- examples and 10 000 validation examples (for selecting hyper-parameters like
+ digit images and it is divided in 60,000 examples for the training set and 
+ 10,000 examples for testing. In many papers as well as in this tutorial, the
+ official training set of 60,000 is divided into an actual training set of 50,000
+ examples and 10,000 validation examples (for selecting hyper-parameters like
  learning rate and size of the model). All digit images have been size-normalized and 
  centered in a fixed size image of 28 x 28 pixels. In the original dataset 
  each pixel of the image is represented by a value between 0 and 255, where 
@@ -60,7 +60,7 @@ MNIST Dataset
 
  .. code-block:: python
 
-   import cPickle, gzip, numpy
+    import cPickle, gzip, numpy
 
     # Load the dataset 
     f = gzip.open('mnist.pkl.gz','rb')