Update digit_recognition.ipynb

Author: adarsh0806

projects/digit_recognition/digit_recognition.ipynb

@@ -30,7 +30,7 @@
     "\n",
     "You can use ** Keras ** to implement your model. Read more at [keras.io](https://keras.io/).\n",
     "\n",
-    "Here is an example of a [published baseline model on this problem](http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/42241.pdf). ([video](https://www.youtube.com/watch?v=vGPI_JvLoN0)). You are not expected to model your architecture precisely using this model nor get the same performance levels, but this is more to show an exampe of an approach used to solve this particular problem. We encourage you to try out different architectures for yourself and see what works best for you. Here is a useful [forum post](https://discussions.udacity.com/t/goodfellow-et-al-2013-architecture/202363) discussing the architecture as described in the paper."
+    "Here is an example of a [published baseline model on this problem](http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/42241.pdf). ([video](https://www.youtube.com/watch?v=vGPI_JvLoN0)). You are not expected to model your architecture precisely using this model nor get the same performance levels, but this is more to show an exampe of an approach used to solve this particular problem. We encourage you to try out different architectures for yourself and see what works best for you. Here is a useful [forum post](https://discussions.udacity.com/t/goodfellow-et-al-2013-architecture/202363) discussing the architecture as described in the paper and here is [another one](https://discussions.udacity.com/t/what-loss-function-to-use-for-multi-digit-svhn-training/176897) discussing the loss function."
    ]
   },
   {