Merge bf39af6 into e6bc7dd

examples/convnet/README.md

@@ -1,13 +1,16 @@
 # ConvNet [![experimental](http://badges.github.io/stability-badges/dist/experimental.svg)](http://github.com/badges/stability-badges) #
 
-This is an example of a 3-layer ConvNet built with Gorgonia. It uses the MNIST data as an example. The MNIST data is not provided, and MUST be put in `../testdata`. 
+This is an example of a 3-layer ConvNet built with Gorgonia. It uses the MNIST data as an example. The MNIST data is not provided, and MUST be put in `../testdata`.
 
 This example currently works but is very slow, pending a change in transpose algorithms.
 
+A step by step tutorial is exposed on to the Gorgonia website: [https://gorgonia.org/tutorials/mnist/](https://gorgonia.org/tutorials/mnist/)
+
 # Disclaimer #
 
 This example comes with a basic implementation of a ConvNet. It does not contain:
 
 * Model serialization (you cannot save your models)
 * Checkpointing.
 * Multithreaded batching (training is highly serial).
+

examples/mnist/README.md

@@ -0,0 +1,7 @@
+This package contains primitives to read the mnist dataset as exposed on [Yann LeCun's website](
+
+It exposes a single `Load` method that creates tensors from the data sets.
+
+Take a look at the [convnet](../convnet) directoy for a neural net implementation using the mnist dataset.
+
+more info on the Gorgonia website: [https://gorgonia.org/tutorials/mnist/](https://gorgonia.org/tutorials/mnist/)