diff --git a/pres.pdf b/pres.pdf
index e14f8a0..930b6db 100644
Binary files a/pres.pdf and b/pres.pdf differ
diff --git a/pres.tex b/pres.tex
index d053afe..c6e78b9 100644
--- a/pres.tex
+++ b/pres.tex
@@ -170,25 +170,22 @@
       \item Should treat model as a black box
       \end{itemize}
 
-      
+      \note{
+        \textbf{Interpretable} \\
+        Use a representation understandable to humans \\
+        Could be a binary vector indicating presence or absence of a word \\
+        Could be a binary vector indicating presence of absence of super-pixels in an image \\
+        \textbf{Fidelity} \\
+        Essentially means the model should be faithful. \\
+        Local fidelity does not imply global fidelity \\
+        The explanation should aim to correspond to how the model behaves in the vicinity of the instance being predicted \\
+        \textbf{Model-agnostic} \\
+        The explanation should be blind to what model is underneath \\
+      }
 
     \end{itemize}
   \end{frame}
 
-  \note[itemize] {
-  \item \textbf{Interpretable}    
-
-  \item Use a representation understandable to humans
-  \item Could be a binary vector indicating presence or absence of a word
-  \item Could be a binary vector indicating presence of absence of super-pixels in an image      
-  \item \textbf{Fidelity}
-  \item Essentially means the model should be faithful.
-  \item Local fidelity does not imply global fidelity
-  \item The explanation should aim to correspond to how the model behaves in the vicinity of the instance being predicted
-  \item \textbf{Model-agnostic}
-      \item The explanation should be blind to what model is underneath
-  }
-
   
 
 
@@ -206,17 +203,16 @@
     \end{itemize}
 
     $$\xi(x) = \operatornamewithlimits{argmin}_{g \in G} \mathcal{L}(f,g,\pi_x) + \Omega(g)$$
+    \note{
+         \textbf{Intepretable models could be:} \\
+          Linear models, decision trees \\
+          $g$ is a vector showing presence or absence of \emph{interpretable components} \\
+          $\Omega(g)$ could be height of a DT or number of non-zero weights of linear model \\
+          In classification, $f(x)$ is the probability or binary indicator that x belongs to a certain class \\
+          So a more complex g will achieve a more faithful interpretation (a lower L), but will increase the value of Omega(g) \\
+    }
   \end{frame}
   
-  \note[itemize] {
-    \item \textbf{Intepretable models could be:}
-    \item Linear models, decision trees
-    \item $g$ is a vector showing presence or absence of \emph{interpretable components}
-    \item $\Omega(g)$ could be height of a DT or number of non-zero weights of linear model
-    \item In classification, $f(x)$ is the probability or binary indicator that x belongs to a certain class
-    \item So a more complex g will achieve a more faithful interpretation (a lower L), but will increase the value of Omega(g)
-  }
-  
 
   \begin{frame}
     \frametitle{Sampling for Local Exploration}
@@ -229,13 +225,14 @@
 
     \center
     \includegraphics[scale=0.15]{graphics/sample_points.png}
-    
+    \note{
+      WTF is x' here? - An interpretable version of x \\
+      g acts in d' while f acts in d, so when we say that we have z' in dimension d', it's the model g, we can recover the z in the original representation i.e. explained by f in dimension d.
+
+    }
   \end{frame}
 
-  \note[itemize] {
-  \item WTF is x' here? - An interpretable version of x
-  \item g acts in d' while f acts in d, so when we say that we have z' in dimension d', it's the model g, we can recover the z in the original representation i.e. explained by f in dimension d.
-  }
+
   
   % \subsubsection{Examples}
 
@@ -277,13 +274,14 @@
 \Return $w$
  \caption{Sparse Linear Explanations using LIME}
 \end{algorithm}
+\note{
+  Talk through the algorithm, discussing the sampling and K-Lasso (least absolute shrinkage and selection operator), which is used for feature selection \\
+ This algorithm approximates the minimization problem of computing a single individual explanation of a prediction. \\
+ K-Lasso is the procedure of learning the weights via least squares. Wtf are these weights??? - The features
+  }
   \end{frame}
 
-  \note[itemize] {
-  \item  Talk through the algorithm, discussing the sampling and K-Lasso (least absolute shrinkage and selection operator), which is used for feature selection
-  \item This algorithm approximates the minimization problem of computing a single individual explanation of a prediction.
-  \item K-Lasso is the procedure of learning the weights via least squares. Wtf are these weights??? - The features
-  }
+
   
   \subsection{Explaining Models}
 
@@ -317,13 +315,14 @@
     \center
     \includegraphics[scale=0.68]{graphics/picker_first.png} \\
     \hspace{1cm}
+    \note{
+ This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not. \\
+ The blue line explains the most inherent feature, which is important, as it is found in most of the instances. \\
+ The red lines indicate the two samples which are most important in explaining the model. \\
+ Thus, explaining importance, is done by:  $I_j = \sqrt{\sum_{i=1}^n W_{ij}}$
+    }
   \end{frame}
-  \note[itemize] {
-  \item This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not.
-  \item The blue line explains the most inherent feature, which is important, as it is found in most of the instances.
-  \item The red lines indicate the two samples which are most important in explaining the model.
-  \item Thus, explaining importance, is done by: $I_j = sqrt(sum_i=1^n W_ij)$
-  }
+
   \begin{frame}
     \frametitle{Picking instances}
         \center
@@ -331,13 +330,14 @@
         \begin{itemize}
         \item  $I_j = \sqrt{\sum_{i=1}^n W_{ij}}$
         \end{itemize}
-  \end{frame}
-    \note[itemize] {
-  \item This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not.
-  \item The blue line explains the most inherent feature, which is important, as it is found in most of the instances.
-  \item The red lines indicate the two samples which are most important in explaining the model.
-  \item Thus, explaining importance, is done by: $I_j = sqrt(sum_i=1^n W_ij)$
-  }
+        \note{
+          This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not. \\
+          The blue line explains the most inherent feature, which is important, as it is found in most of the instances. \\
+          The red lines indicate the two samples which are most important in explaining the model. \\
+          Thus, explaining importance, is done by:  $I_j = \sqrt{\sum_{i=1}^n W_{ij}}$
+        }
+      \end{frame}
+
   \begin{frame}
     \frametitle{Picking instances}
         \center
@@ -345,13 +345,14 @@
         \begin{itemize}
         \item  $I_j = \sqrt{\sum_{i=1}^n W_{ij}}$
         \end{itemize}
-  \end{frame}
-    \note[itemize] {
-  \item This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not.
-  \item The blue line explains the most inherent feature, which is important, as it is found in most of the instances.
-  \item The red lines indicate the two samples which are most important in explaining the model.
-  \item Thus, explaining importance, is done by: $I_j = \sqrt(\sum_{i=1}^n W_ij)$
-  }
+        \note{
+          This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not. \\
+          The blue line explains the most inherent feature, which is important, as it is found in most of the instances. \\
+          The red lines indicate the two samples which are most important in explaining the model. \\
+          Thus, explaining importance, is done by:  $I_j = \sqrt{\sum_{i=1}^n W_{ij}}$
+        }
+      \end{frame}
+
   \begin{frame}
     \frametitle{Picking instances}
         \center
@@ -359,14 +360,14 @@
         \begin{itemize}
         \item  $I_j = \sqrt{\sum_{i=1}^n W_{ij}}$
         \end{itemize}
+        \note{
+          This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not. \\
+          The blue line explains the most inherent feature, which is important, as it is found in most of the instances. \\
+          The red lines indicate the two samples which are most important in explaining the model. \\
+          Thus, explaining importance, is done by:  $I_j = \sqrt{\sum_{i=1}^n W_{ij}}$
+        }
+      \end{frame}
 
-  \end{frame}
-  \note[itemize] {
-  \item This is a matrix explaining instances and their features explained by a binary list s.t. an instance either has a feature or does not.
-  \item The blue line explains the most inherent feature, which is important, as it is found in most of the instances.
-  \item The red lines indicate the two samples which are most important in explaining the model.
-  \item Thus, explaining importance, is done by: $I_j = sqrt(sum_i=1^n W_ij)$
-  }
  
   \begin{frame}
     \frametitle{Submodular Picks}