Pownie/adm-pres
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

comment fixerino

Browse Source
This commit is contained in:
Alexander Munch-Hansen 2019-11-27 22:26:30 +01:00
parent 261b37419d
commit 48dc576076
2 changed files with 62 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
pres.pdf
View File

Binary file not shown.

123
pres.tex
View File

@ -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}