small cosmetic changes

docs/backpropagation.rst

@@ -7,8 +7,8 @@ Backpropagation
 The goals of backpropagation are straightforward: adjust each weight in the network in proportion to how much it contributes to overall error. If we iteratively reduce each weight's error, eventually we’ll have a series of weights the produce good predictions.
 
 
-Chain rule review
-=================
+Chain rule refresher
+====================
 
 As seen above, foward propagation can be viewed as a long series of nested equations. If you think of feed forward this way, then backpropagation is merely an application the :ref:`chain_rule` to find the :ref:`derivative` of cost with respect to any variable in the nested equation. Given a forward propagation function:
 
@@ -82,8 +82,8 @@ See the pattern? The number of calculations required to compute cost derivatives
 
 
 
-Memoization
-===========
+Saving work with memoization
+============================
 
 Memoization is a computer science term which simply means: don’t recompute the same thing over and over. In memoization we store previously computed results to avoid recalculating the same function. It's handy for speeding up recursive functions of which backpropagation is one. Notice the pattern in the derivative equations below.
 

docs/basics.rst

@@ -48,6 +48,17 @@ References:
 * <http://people.duke.edu/~rnau/regintro.htm>
 * <https://en.wikipedia.org/wiki/Linear_regression>
 
+Logistic Regression
+===================
+
+Be the first to contribute!
+
+
+Cost Functions
+==============
+
+Be the first to contribute!
+
 
 Gradient Descent
 ================

docs/glossary.rst

@@ -30,7 +30,7 @@ Bias Metric
 
   - **High bias** (with low variance) suggests your model may be underfitting and you're using the wrong architecture for the job.
 
-.. _ bias_term:
+.. _bias_term:
 
 Bias Term
   Allow models to represent patterns that do not pass through the origin. For example, if all my features were 0, would my output also be zero? Is it possible there is some base value upon which my features have an effect? Bias terms typically accompany weights and are attached to neurons or filters.

docs/nn_concepts.rst

@@ -29,7 +29,6 @@ Synapse
 Synapses are like roads in a neural network. They connect inputs to neurons, neurons to neurons, and neurons to outputs. In order to get from one neuron to another, you have to travel along the synapse paying the “toll” (weight) along the way. Each connection between two neurons has a unique synapse with a unique weight attached to it. When we talk about updating weights in a network, we’re really talking about adjusting the weights on these synapses.
 
 
-
 Weights
 =======
 
@@ -39,7 +38,7 @@ Explanation of weights (parameters)
 Bias
 ====
 
-Bias terms are additional constants attached to neurons and added to the weighted input before the activation function is applied. A more detailed explanation of :ref:`bias_term` is available in the glossary.
+Bias terms are additional constants attached to neurons and added to the weighted input before the activation function is applied. Bias terms help models represent patterns that do not necessarily pass through the origin. For example, if all your features were 0, would your output also be zero? Is it possible there is some base value upon which your features have an effect? Bias terms typically accompany weights and must also be learned by your model.
 
 
 Layers
@@ -101,13 +100,6 @@ Activation functions typically have the following properties:
 
 
 
-Loss Functions
-==============
-
-Be the first to contribute!
-
-
-
 
 
 .. rubric:: References