WIP: fixes #3, #6; l2 & l1 loss added (#7)

* README UPDATE: modified git clone address; added python3 dependency installation

* L1 & L2 added for batch loss

* update readme repo link & python3 info added

* l2 and l1 losses added to the code but not in blog

README.md

@@ -6,7 +6,7 @@
 
 1. Clone Repo
 ```
-git clone https://github.com/bfortuner/ml-glossary
+git clone https://github.com/bfortuner/ml-cheatsheet.git
 ```
 
 2. Install Dependencies
@@ -16,7 +16,12 @@ pip install sphinx sphinx-autobuild
 pip install sphinx_rtd_theme
 pip install recommonmark
 ```
-
+For python-3.x installed, use:
+```
+pip3 install sphinx sphinx-autobuild
+pip3 install sphinx_rtd_theme
+pip3 install recommonmark
+```
 3. Preview Changes
 ```
 cd ml-cheatsheet
@@ -81,6 +86,7 @@ We'd also like to publish top entries to our Medium Blog, for even more visibili
 ## Tips and Tricks
 
 * [Adding equations](http://www.sphinx-doc.org/en/stable/ext/math.html)
+* [Working with Jupyter Notebook](http://louistiao.me/posts/demos/ipython-notebook-demo/)
 * Quickstart with Jupyter notebook template
 * Graphs and charts
 * Importing images
@@ -97,5 +103,4 @@ We'd also like to publish top entries to our Medium Blog, for even more visibili
 * [Embedding Math Equations](http://www.sphinx-doc.org/en/stable/ext/math.html)
 * [Sphinx Tutorial](https://pythonhosted.org/an_example_pypi_project/sphinx.html)
 * [Sphinx Docs](http://www.sphinx-doc.org/en/stable/markup/code.html)
-* [Sphinx Cheatsheet](http://openalea.gforge.inria.fr/doc/openalea/doc/_build/html/source/sphinx/rest_syntax.html)
-
+* [Sphinx Cheatsheet](http://openalea.gforge.inria.fr/doc/openalea/doc/_build/html/source/sphinx/rest_syntax.html)

code/loss_functions.py

@@ -1,6 +1,8 @@
 import math
 import numpy as np
 
+# using the common convention:
+#	yHat is the prediction while y is the truth (true label)
 
 def CrossEntropy(yHat, y):
     pass
@@ -14,12 +16,12 @@ def KLDivergence(yHat, y):
     pass
 
 
-def L1(yHat, y):
-    pass
+def L1(yHat, y):s
+    return np.sum(np.absolute(yHat - y))
 
 
 def L2(yHat, y):
-    pass
+    return np.sum((yHat - y)**2)
 
 
 def MLE(yHat, y):