Documentatiob adapted

MelJan · Apr 7, 2017 · 79512a6 · 79512a6
1 parent 4fd78e1
commit 79512a6
Show file tree

Hide file tree

Showing 3 changed files with 51 additions and 2 deletions.
diff --git a/docs/index.rst b/docs/index.rst
@@ -3,12 +3,15 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
+================================================
+Welcome to PyDeep's documentation!
+================================================
+
 .. toctree::
    :maxdepth: 8
    :caption: Contents:
 
-================================================
-Welcome to PyDeep's documentation!
+Welcome
 ================================================
 .. toctree::
    :maxdepth: 2

diff --git a/docs/installation.rst b/docs/installation.rst
@@ -2,4 +2,45 @@ Installation
 ##################################
 
 
+To install PyDeep, simply change to the PyDeep folder and run the setup script:
 
+.. code-block:: bash
+
+    python setup.py install
+
+Dependencies
+============
+
+PyDeep has the following dependencies:
+
+Hard dependencies:
+----------------------------------------------------
+
+- numpy
+
+- scipy
+
+Soft dependencies:
+----------------------------------------------------
+
+-matplotlib
+
+- cPickle
+
+- encryptedpickle
+
+- paramiko
+
+- mdp
+
+
+Optimized backend:
+============================================================
+
+It is highly recommended to use an multi-threading optimized linear algebra backend such as
+
+-  `Automatically Tuned Linear Algebra Software (ATLAS) <https://software.intel.com/en-us/intel-mkl/>`_
+
+-  `Intel® Math Kernel Library (Intel® MKL)  http://math-atlas.sourceforge.net/>`_
+
+MKL is inlcuded in `Enthought <https://www.enthought.com/>`_ which provides a free academic license.
diff --git a/docs/welcome.rst b/docs/welcome.rst
@@ -6,8 +6,11 @@ The library has a modular design, is well documented and  purely written in Pyth
 This allows you to understand, use, modify, and debug the code easily. Furthermore,
 its extensive use of unittests assures a high level of reliability and correctness.
 
+
+
 The library contains code I have written during my PhD research allowing you to reproduce
 the results described in the following publications.
+
 - `Gaussian-binary restricted Boltzmann machines for modeling natural image statistics. Melchior, J., Wang, N., & Wiskott, L.. (2017). PLOS ONE, 12(2), 1–24. <http://doi.org/10.1371/journal.pone.0171015>`_
 
 - `How to Center Deep Boltzmann Machines. Melchior, J., Fischer, A., & Wiskott, L.. (2016). Journal of Machine Learning Research, 17(99), 1–61. <http://jmlr.org/papers/v17/14-237.html>`_
@@ -20,6 +23,8 @@ the results described in the following publications.
 
 - `Learning Natural Image Statistics with Gaussian-Binary Restricted Boltzmann Machines. Melchior, J, 29.05.2012. Master’s thesis, Applied Computer Science, Univ. of Bochum, Germany. <https://www.ini.rub.de/PEOPLE/wiskott/Reprints/Melchior-2012-MasterThesis-RBMs.pdf>`_
 
+IF you want to use PyDeep in your publication, you can cite it as follows.
+
 .. code-block:: latex
 
    @misc{melchior2017pydeep,