some small changes and reorgs

braingineer · braingineer · commit 68cc30a4e574 · 2018-05-01T10:22:39.000-04:00
diff --git a/docs/day2/patterns/attention.rst b/docs/day2/patterns/attention.rst
@@ -1,5 +1,5 @@
-Attention
-=========
+Design Pattern: Attention
+=========================
 
 Attention is a useful pattern for when you want to take a collection of vectors---whether it be a sequence of vectors representing a sequence of words, or an unordered collections of vectors representing a collection of attributes---and summarize them into a single vector.  This has similar analogs to the CBOW examples we saw on Day 1, but instead of just averaging or using max pooling, we are learning a function which learns to compute the weights for each of the vectors before summing them together.
 
diff --git a/docs/day2/sampling.rst b/docs/day2/sampling.rst
@@ -1,5 +1,5 @@
-Sampling from an RNN
-====================
+Exercise: Sampling from an RNN
+==============================
 
 The goal of sampling from an RNN is to initialize the sequence in some way, feed it into the recurrent computation, and retrieve the next prediction. 
 
diff --git a/docs/index.rst b/docs/index.rst
@@ -30,9 +30,9 @@ Natural Language Processing (NLP) with PyTorch
    day2/warmup
    day2/failfastprototypemode
    day2/tensorfu1
-   day2/sampling
    day2/tensorfu2
    day2/adventures/interpolation
+   day2/sampling
    day2/patterns/attention
 
 
