add layer collection and metrics documentation

docs/api/layercollection.rst

@@ -0,0 +1,16 @@
+Layer collection
+================
+
+Layer collections describe the structure of parameters that will be differentiated. We need the LayerCollection object in order to be able to map components of different objects together. As an example, when performing a matrix-vector product using a block diagonal representation, we need to make sure that elements of the vector corresponding to parameters from layer 1 are multiplied with the diagonal block also corresponding to parameters from layer 1, and so on.
+
+Typical use cases include:
+
+ - All parameters of your network: for this you can simply use the constructor :func:`nngeometry.layercollection.LayerCollection.from_model`
+ - Only parameters from some layers of your network. In this case you need to
+  1. instantiate a new LayerCollection object
+  2. add your layers one at a time using :func:`nngeometry.layercollection.LayerCollection.add_layer_from_model`
+
+
+.. automodule:: nngeometry.layercollection
+    :members:
+    :undoc-members:

docs/api/metrics.rst

@@ -0,0 +1,7 @@
+Metrics
+=======
+
+Metrics introduction 
+
+.. automodule:: nngeometry.metrics
+    :members:

nngeometry/metrics.py

@@ -9,8 +9,8 @@ def FIM_MonteCarlo1(layer_collection,
                     representation,
                     variant='classif_logsoftmax'):
     """
-    Helper to create a matrix computing the Fisher Information
-    Matrix using a Monte-Carlo estimate with 1 sample per example
+    Helper that creates a matrix computing the Fisher Information
+    Matrix using a Monte-Carlo estimate of y|x with 1 sample per example
     """
 
     if variant == 'classif_logsoftmax':
@@ -39,7 +39,7 @@ def FIM(layer_collection,
         variant='classif_logits',
         device='cpu'):
     """
-    Helper to create a matrix computing the Fisher Information
+    Helper that creates a matrix computing the Fisher Information
     Matrix using closed form expressions for the expectation y|x
     as described in (Pascanu and Bengio, 2013)
     """