initial push
|
@ -0,0 +1,5 @@
|
|||
<frame >
|
||||
|
||||
<titlepage>
|
||||
|
||||
</frame>
|
|
@ -0,0 +1,19 @@
|
|||
<frame title="Thesis@ls9">
|
||||
<list>
|
||||
<e>First: Find a topic and a supervisor</e>
|
||||
<e>Work one month on this, to make sure</e>
|
||||
<l2st>
|
||||
<e>you still like your topic</e>
|
||||
<e>and you are sure you can handle the topic</e>
|
||||
</l2st>
|
||||
<e>then short presentation in front of our chair (15min, relaxed)</e>
|
||||
<l2st>
|
||||
<e>get some feedback/suggestions</e>
|
||||
</l2st>
|
||||
<e>afterwards register the thesis</e>
|
||||
<l2st>
|
||||
<e>(different for CS/DS students)</e>
|
||||
</l2st>
|
||||
<e>Problem: We are not able to supervise more than 2 students at the same time (CS faculty rules)</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,7 @@
|
|||
<frame title="Today">
|
||||
<list>
|
||||
<e>First: A short summary of each Topic</e>
|
||||
<e>Then time for questions/Talk with your supervisor about each topic that sounds interesting</e>
|
||||
<e>Your own topics are always welcome;)</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,13 @@
|
|||
<frame title="Anomaly Detection">
|
||||
<split>
|
||||
<que>
|
||||
<list>
|
||||
<e>Im working on Anomaly Detection</e>
|
||||
<e>That means characterising an often very complex distributions, to find events that dont match the expected distribution</e>
|
||||
</list>
|
||||
</que>
|
||||
<que>
|
||||
<i f="../prep/03Anomaly_Detection/circle.pdf" wmode="True"></i>
|
||||
</que>
|
||||
</split>
|
||||
</frame>
|
|
@ -0,0 +1,8 @@
|
|||
<frame title="knn">
|
||||
<list>
|
||||
<e>kNN algorithm can also be used for AD</e>
|
||||
<e>if the k closest point is further away, a sample is considered more anomalous</e>
|
||||
<e>$r=\frac{k}{2N\cdot pdf}$</e>
|
||||
<e>Powerful method, as it can model the pdf directly</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,8 @@
|
|||
<frame title="Better knn">
|
||||
<list>
|
||||
<e>The model (mostly) ignores every known sample except one</e>
|
||||
<e>So there are extensions</e>
|
||||
<e>$avg=\frac{1}{N} \sum_i knn_i(x)$</e>
|
||||
<e>$wavg=\frac{1}{N} \sum_i \frac{knn_i(x)}{i}$</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,5 @@
|
|||
<frame title="Comparison">
|
||||
<list>
|
||||
<e>nothing</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,13 @@
|
|||
<frame title="What to do?">
|
||||
<list>
|
||||
<e>Evaluation as anomaly detector is complicated</e>
|
||||
<l2st>
|
||||
<e>Requires known anomalies</e>
|
||||
</l2st>
|
||||
<e>->So evaluate as density estimator</e>
|
||||
<l2st>
|
||||
<e>Does not require anomalies</e>
|
||||
<e>Allows generating infinite amounts of training data</e>
|
||||
</l2st>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,8 @@
|
|||
<frame title="What to do?">
|
||||
<list>
|
||||
<e>Collect Extensions of the oc-knn algorithm</e>
|
||||
<e>Define some distance measure to a known pdf</e>
|
||||
<e>Generate random datapoints following the pdf</e>
|
||||
<e>Evaluate which algorithm finds the pdf the best</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,12 @@
|
|||
<frame title="Requirements">
|
||||
<list>
|
||||
<e>Knowledge of python ( sum([i for i in range(5) if i\%2]) )</e>
|
||||
<l2st>
|
||||
<e>Ideally incl numpy</e>
|
||||
</l2st>
|
||||
<e>Basic university level Math (you could argue that $r_k \propto \frac{k}{pdf}$)</e>
|
||||
<e>Ideally some experience working on a ssh server</e>
|
||||
<e>->Good as a Bachelor Thesis</e>
|
||||
<e>For a Master Thesis, I would extend this a bit (Could you also find $k$?)</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,9 @@
|
|||
<frame title="Normalising Flows">
|
||||
<list>
|
||||
<e>Deep Learning Method, in which the output is normalised</e>
|
||||
<e>$\int f(x) dx=1 \; \forall f(x)$</e>
|
||||
<e>Can be used to estimate probability density functions</e>
|
||||
<e>->Thus useful for AD</e>
|
||||
<e>$\int f(h(x)) \|\frac{\delta h}{\delta x}\| dx=1 \; \forall h(x)$</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,10 @@
|
|||
<frame title="Graph Normalising Flows">
|
||||
<list>
|
||||
<e>How to apply this to graphs?</e>
|
||||
<e>One Paper (Liu 2019) uses two NN:</e>
|
||||
<e>Autoencoder graph->vector</e>
|
||||
<e>NF on vector data</e>
|
||||
<e>which is fine, but also not really graph specific</e>
|
||||
<e>No interaction between encoding and transformation</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,14 @@
|
|||
<frame title="Graph Normalising Flows">
|
||||
<list>
|
||||
<e>So why not do this directly?</e>
|
||||
<e>->Requires differentiating a graph</e>
|
||||
<e>Why not use only one Network?</e>
|
||||
<e>Graph->Vector->pdf</e>
|
||||
<e>->Finds trivial solution, as $<pdf> \propto \frac{1}{\sigma_{Vector}}$</e>
|
||||
<e>So regularise the standart deviation of the vector space!</e>
|
||||
<l2st>
|
||||
<e>Interplay between encoding and NF</e>
|
||||
<e>Could also be useful for highdim data</e>
|
||||
</l2st>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,13 @@
|
|||
<frame title="Requirements">
|
||||
<list>
|
||||
<e>Proficient in python ( [i for i in range(1,N) if not [j for j in range(2,i) if not i\%j]] )</e>
|
||||
<l2st>
|
||||
<e>Ideally incl numpy, tensorflow, keras</e>
|
||||
</l2st>
|
||||
<e>Some deep learning experience</e>
|
||||
<e>University level math (google Cholesky Decomposition. Why is this useful for NF?)</e>
|
||||
<e>Ideally some experience working on a ssh server</e>
|
||||
<e>A bit more challenging->Better as a Master thesis</e>
|
||||
<e>(Still we would start very slowly of course)</e>
|
||||
</list>
|
||||
</frame>
|
|
@ -0,0 +1,14 @@
|
|||
<frame title="Old Thesis Sina">
|
||||
<split>
|
||||
<que>
|
||||
<list>
|
||||
<e>Isolation Forest: Different Anomaly Detection Algorithm</e>
|
||||
<e>Problem: Isolation Forests dont work on categorical data</e>
|
||||
<e>->Extend them to categorical data</e>
|
||||
</list>
|
||||
</que>
|
||||
<que>
|
||||
<i f="../prep/20Old_Thesis_Sina/Bildschirmfoto vom 2022-09-26 16-22-30.png" wmode="True"></i>
|
||||
</que>
|
||||
</split>
|
||||
</frame>
|
|
@ -0,0 +1,14 @@
|
|||
<frame title="Old Thesis Britta">
|
||||
<split>
|
||||
<que>
|
||||
<list>
|
||||
<e>Reidentification: Find known objects in new images</e>
|
||||
<e>Task: Find if two images of pallet blocks are of the same pallet block</e>
|
||||
<e>Use AD to represent the pallet blocks</e>
|
||||
</list>
|
||||
</que>
|
||||
<que>
|
||||
<i f="../prep/21Old_Thesis_Britta/Bildschirmfoto vom 2022-09-26 16-23-26.png" wmode="True"></i>
|
||||
</que>
|
||||
</split>
|
||||
</frame>
|
|
@ -0,0 +1,13 @@
|
|||
<frame title="Old Thesis Hsin Ping">
|
||||
<split>
|
||||
<que>
|
||||
<list>
|
||||
<e>Ensemble: Combination of multiple models</e>
|
||||
<e>Task: Explain the prediction of a model using the ensemble structure</e>
|
||||
</list>
|
||||
</que>
|
||||
<que>
|
||||
<i f="../prep/22Old_Thesis_Hsin_Ping/Bildschirmfoto vom 2022-09-26 16-24-14.png" wmode="True"></i>
|
||||
</que>
|
||||
</split>
|
||||
</frame>
|
|
@ -0,0 +1,13 @@
|
|||
<frame title="Old Thesis Nikitha">
|
||||
<split>
|
||||
<que>
|
||||
<list>
|
||||
<e>Task: Explore a new kind of ensemble</e>
|
||||
<e>Instead of many uncorrelated models, let the models interact during training</e>
|
||||
</list>
|
||||
</que>
|
||||
<que>
|
||||
<i f="../prep/23Old_Thesis_Nikitha/Bildschirmfoto vom 2022-09-26 16-25-06.png" wmode="True"></i>
|
||||
</que>
|
||||
</split>
|
||||
</frame>
|
|
@ -0,0 +1,12 @@
|
|||
<plt>
|
||||
|
||||
<name Current experiment status>
|
||||
<title Open Thesis Topics>
|
||||
<stitle Thesis Simon>
|
||||
|
||||
<institute ls9 tu Dortmund>
|
||||
|
||||
<theme CambridgeUS>
|
||||
<colo dolphin>
|
||||
|
||||
</plt>
|
|
@ -0,0 +1,6 @@
|
|||
Two distributions
|
||||
<l2st>
|
||||
One known (=normal)
|
||||
One unknown (=anomalies)
|
||||
</l2st>
|
||||
Seperate them
|
|
@ -0,0 +1,7 @@
|
|||
Two distributions
|
||||
<l2st>
|
||||
One known (=normal)
|
||||
One unknown (=anomalies)
|
||||
</l2st>
|
||||
Seperate them
|
||||
Problem: few anomalies
|
|
@ -0,0 +1,8 @@
|
|||
Anomalies are rare, so often only a few datapoints known (e.g. Machine Failure in an Aircraft)
|
||||
In practice, anomalies might appear that are not known during testing
|
||||
->So train the model only on normal samples
|
||||
Unsupervised Machine Learning
|
||||
<l2st>
|
||||
What can we say without knowing anomalies?
|
||||
''Understand you dataset''
|
||||
</l2st>
|
|
@ -0,0 +1,8 @@
|
|||
Anomalies are rare, so often only a few datapoints known (e.g. Machine Failure in an Aircraft)
|
||||
In practice, anomalies might appear that are not known during testing
|
||||
->So train the model only on normal samples
|
||||
Unsupervised Machine Learning
|
||||
<l2st>
|
||||
What can we say without knowing anomalies?
|
||||
''Understand you dataset''
|
||||
</l2st>
|
After Width: | Height: | Size: 648 KiB |
|
@ -0,0 +1,6 @@
|
|||
Seems easy? Now do this
|
||||
<l2st>
|
||||
in thousands of dimensions
|
||||
with complicated distributions
|
||||
and overlap between anomalies and normal points
|
||||
</l2st>
|
After Width: | Height: | Size: 47 KiB |
|
@ -0,0 +1,3 @@
|
|||
Most machine learning requires Hyperparameter Optimisation
|
||||
(Find model parameters that result in the best results)
|
||||
->AutoML: Do this automatically as fast as possible
|
|
@ -0,0 +1,9 @@
|
|||
So lets combine both (Auto Anomaly Detection)
|
||||
->Problem
|
||||
<l2st>
|
||||
AutoMl requires Evaluation (loss, accuracy, AUC) to optimize
|
||||
AD can only be evaluated with regards to the anomalies
|
||||
->no longer unsupervised
|
||||
</l2st>
|
||||
So most Anomaly Detection is ''unoptimized''
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
So how to solve this?
|
||||
One option: Think of some function to evaluate only the normal points
|
||||
->A bit hard to do in a case study
|
|
@ -0,0 +1,5 @@
|
|||
So how to solve this?
|
||||
One option: ''Just find the best solution directly''
|
||||
->Zero Shot AutoML
|
||||
Find best practices for hyperparameters
|
||||
Requires optimisation for each model seperately -> matches the case study structure quite well!
|
|
@ -0,0 +1,12 @@
|
|||
Basics of Scientific Computing
|
||||
Basics of AD
|
||||
Basics of AutoML
|
||||
Build groups for each algorithm
|
||||
<l2st>
|
||||
Choose a set of Hyperparameters
|
||||
Find ''best practice`s'' for them
|
||||
Maybe consider more complicated Transformations (Preprocessing, Ensemble)
|
||||
</l2st>
|
||||
Compare between groups (best algorithm for current situation)
|
||||
Evaluate on new datasets
|
||||
Write a report/Present your work
|
After Width: | Height: | Size: 80 KiB |
|
@ -0,0 +1,7 @@
|
|||
Requirements:
|
||||
<l2st>
|
||||
MD Req 1->MD Req 8
|
||||
Basic Python/Math Knowledge
|
||||
Motivation to learn something new;)
|
||||
</l2st>
|
||||
Registration till Saturday, by Email to Simon.Kluettermann@cs.tu-dortmund.de
|
|
@ -0,0 +1,3 @@
|
|||
pdflatex main.tex
|
||||
pdflatex main.tex
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
pdflatex main.tex
|
||||
pdflatex main.tex
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
[
|
||||
{
|
||||
"typ": "img",
|
||||
"files": [
|
||||
"../prep/03Anomaly_Detection/circle.pdf"
|
||||
],
|
||||
"label": "prep03Anomaly_Detectioncirclepdf",
|
||||
"caption": "",
|
||||
"where": "../knn1//data/003Anomaly Detection.txt"
|
||||
},
|
||||
{
|
||||
"typ": "img",
|
||||
"files": [
|
||||
"../prep/20Old_Thesis_Sina/Bildschirmfoto vom 2022-09-26 16-22-30.png"
|
||||
],
|
||||
"label": "prep20Old_Thesis_SinaBildschirmfoto vom 2022-09-26 16-22-30png",
|
||||
"caption": "",
|
||||
"where": "../knn1//data/014Old Thesis Sina.txt"
|
||||
},
|
||||
{
|
||||
"typ": "img",
|
||||
"files": [
|
||||
"../prep/21Old_Thesis_Britta/Bildschirmfoto vom 2022-09-26 16-23-26.png"
|
||||
],
|
||||
"label": "prep21Old_Thesis_BrittaBildschirmfoto vom 2022-09-26 16-23-26png",
|
||||
"caption": "",
|
||||
"where": "../knn1//data/015Old Thesis Britta.txt"
|
||||
},
|
||||
{
|
||||
"typ": "img",
|
||||
"files": [
|
||||
"../prep/22Old_Thesis_Hsin_Ping/Bildschirmfoto vom 2022-09-26 16-24-14.png"
|
||||
],
|
||||
"label": "prep22Old_Thesis_Hsin_PingBildschirmfoto vom 2022-09-26 16-24-14png",
|
||||
"caption": "",
|
||||
"where": "../knn1//data/016Old Thesis Hsin Ping.txt"
|
||||
},
|
||||
{
|
||||
"typ": "img",
|
||||
"files": [
|
||||
"../prep/23Old_Thesis_Nikitha/Bildschirmfoto vom 2022-09-26 16-25-06.png"
|
||||
],
|
||||
"label": "prep23Old_Thesis_NikithaBildschirmfoto vom 2022-09-26 16-25-06png",
|
||||
"caption": "",
|
||||
"where": "../knn1//data/017Old Thesis Nikitha.txt"
|
||||
}
|
||||
]
|
|
@ -0,0 +1,140 @@
|
|||
\relax
|
||||
\providecommand\hyper@newdestlabel[2]{}
|
||||
\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}
|
||||
\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined
|
||||
\global\let\oldcontentsline\contentsline
|
||||
\gdef\contentsline#1#2#3#4{\oldcontentsline{#1}{#2}{#3}}
|
||||
\global\let\oldnewlabel\newlabel
|
||||
\gdef\newlabel#1#2{\newlabelxx{#1}#2}
|
||||
\gdef\newlabelxx#1#2#3#4#5#6{\oldnewlabel{#1}{{#2}{#3}}}
|
||||
\AtEndDocument{\ifx\hyper@anchor\@undefined
|
||||
\let\contentsline\oldcontentsline
|
||||
\let\newlabel\oldnewlabel
|
||||
\fi}
|
||||
\fi}
|
||||
\global\let\hyper@last\relax
|
||||
\gdef\HyperFirstAtBeginDocument#1{#1}
|
||||
\providecommand\HyField@AuxAddToFields[1]{}
|
||||
\providecommand\HyField@AuxAddToCoFields[2]{}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{1}{1/1}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {1}{1}}}
|
||||
\newlabel{Thesis@ls9<1>}{{2}{2}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Thesis@ls9<1>}{2}}
|
||||
\newlabel{Thesis@ls9}{{2}{2}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Thesis@ls9}{2}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{2}{2/2}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {2}{2}}}
|
||||
\newlabel{Today<1>}{{3}{3}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Today<1>}{3}}
|
||||
\newlabel{Today}{{3}{3}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Today}{3}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{3}{3/3}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {3}{3}}}
|
||||
\newlabel{Anomaly Detection<1>}{{4}{4}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Anomaly Detection<1>}{4}}
|
||||
\newlabel{Anomaly Detection}{{4}{4}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Anomaly Detection}{4}}
|
||||
\newlabel{fig:prep03Anomaly_Detectioncirclepdf}{{4}{4}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {fig:prep03Anomaly_Detectioncirclepdf}{4}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{4}{4/4}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {4}{4}}}
|
||||
\newlabel{knn<1>}{{5}{5}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {knn<1>}{5}}
|
||||
\newlabel{knn}{{5}{5}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {knn}{5}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{5}{5/5}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {5}{5}}}
|
||||
\newlabel{Better knn<1>}{{6}{6}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Better knn<1>}{6}}
|
||||
\newlabel{Better knn}{{6}{6}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Better knn}{6}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{6}{6/6}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {6}{6}}}
|
||||
\newlabel{Comparison<1>}{{7}{7}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Comparison<1>}{7}}
|
||||
\newlabel{Comparison}{{7}{7}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Comparison}{7}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{7}{7/7}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {7}{7}}}
|
||||
\newlabel{What to do?<1>}{{8}{8}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {What to do?<1>}{8}}
|
||||
\newlabel{What to do?}{{8}{8}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {What to do?}{8}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{8}{8/8}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {8}{8}}}
|
||||
\newlabel{What to do?<1>}{{9}{9}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {What to do?<1>}{9}}
|
||||
\newlabel{What to do?}{{9}{9}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {What to do?}{9}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{9}{9/9}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {9}{9}}}
|
||||
\newlabel{Requirements<1>}{{10}{10}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Requirements<1>}{10}}
|
||||
\newlabel{Requirements}{{10}{10}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Requirements}{10}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{10}{10/10}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {10}{10}}}
|
||||
\newlabel{Normalising Flows<1>}{{11}{11}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Normalising Flows<1>}{11}}
|
||||
\newlabel{Normalising Flows}{{11}{11}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Normalising Flows}{11}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{11}{11/11}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {11}{11}}}
|
||||
\newlabel{Graph Normalising Flows<1>}{{12}{12}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Graph Normalising Flows<1>}{12}}
|
||||
\newlabel{Graph Normalising Flows}{{12}{12}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Graph Normalising Flows}{12}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{12}{12/12}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {12}{12}}}
|
||||
\newlabel{Graph Normalising Flows<1>}{{13}{13}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Graph Normalising Flows<1>}{13}}
|
||||
\newlabel{Graph Normalising Flows}{{13}{13}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Graph Normalising Flows}{13}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{13}{13/13}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {13}{13}}}
|
||||
\newlabel{Requirements<1>}{{14}{14}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Requirements<1>}{14}}
|
||||
\newlabel{Requirements}{{14}{14}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Requirements}{14}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{14}{14/14}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {14}{14}}}
|
||||
\newlabel{Old Thesis Sina<1>}{{15}{15}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Sina<1>}{15}}
|
||||
\newlabel{Old Thesis Sina}{{15}{15}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Sina}{15}}
|
||||
\newlabel{fig:prep20Old_Thesis_SinaBildschirmfoto vom 2022-09-26 16-22-30png}{{15}{15}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {fig:prep20Old_Thesis_SinaBildschirmfoto vom 2022-09-26 16-22-30png}{15}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{15}{15/15}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {15}{15}}}
|
||||
\newlabel{Old Thesis Britta<1>}{{16}{16}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Britta<1>}{16}}
|
||||
\newlabel{Old Thesis Britta}{{16}{16}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Britta}{16}}
|
||||
\newlabel{fig:prep21Old_Thesis_BrittaBildschirmfoto vom 2022-09-26 16-23-26png}{{16}{16}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {fig:prep21Old_Thesis_BrittaBildschirmfoto vom 2022-09-26 16-23-26png}{16}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{16}{16/16}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {16}{16}}}
|
||||
\newlabel{Old Thesis Hsin Ping<1>}{{17}{17}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Hsin Ping<1>}{17}}
|
||||
\newlabel{Old Thesis Hsin Ping}{{17}{17}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Hsin Ping}{17}}
|
||||
\newlabel{fig:prep22Old_Thesis_Hsin_PingBildschirmfoto vom 2022-09-26 16-24-14png}{{17}{17}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {fig:prep22Old_Thesis_Hsin_PingBildschirmfoto vom 2022-09-26 16-24-14png}{17}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{17}{17/17}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {17}{17}}}
|
||||
\newlabel{Old Thesis Nikitha<1>}{{18}{18}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Nikitha<1>}{18}}
|
||||
\newlabel{Old Thesis Nikitha}{{18}{18}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {Old Thesis Nikitha}{18}}
|
||||
\newlabel{fig:prep23Old_Thesis_NikithaBildschirmfoto vom 2022-09-26 16-25-06png}{{18}{18}{}{Doc-Start}{}}
|
||||
\@writefile{snm}{\beamer@slide {fig:prep23Old_Thesis_NikithaBildschirmfoto vom 2022-09-26 16-25-06png}{18}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{18}{18/18}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {18}{18}}}
|
||||
\@writefile{nav}{\headcommand {\slideentry {0}{0}{19}{19/19}{}{0}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@framepages {19}{19}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@partpages {1}{19}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@subsectionpages {1}{19}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@sectionpages {1}{19}}}
|
||||
\@writefile{nav}{\headcommand {\beamer@documentpages {19}}}
|
||||
\@writefile{nav}{\headcommand {\gdef \inserttotalframenumber {19}}}
|
||||
\gdef \@abspage@last{19}
|
|
@ -0,0 +1,43 @@
|
|||
\headcommand {\slideentry {0}{0}{1}{1/1}{}{0}}
|
||||
\headcommand {\beamer@framepages {1}{1}}
|
||||
\headcommand {\slideentry {0}{0}{2}{2/2}{}{0}}
|
||||
\headcommand {\beamer@framepages {2}{2}}
|
||||
\headcommand {\slideentry {0}{0}{3}{3/3}{}{0}}
|
||||
\headcommand {\beamer@framepages {3}{3}}
|
||||
\headcommand {\slideentry {0}{0}{4}{4/4}{}{0}}
|
||||
\headcommand {\beamer@framepages {4}{4}}
|
||||
\headcommand {\slideentry {0}{0}{5}{5/5}{}{0}}
|
||||
\headcommand {\beamer@framepages {5}{5}}
|
||||
\headcommand {\slideentry {0}{0}{6}{6/6}{}{0}}
|
||||
\headcommand {\beamer@framepages {6}{6}}
|
||||
\headcommand {\slideentry {0}{0}{7}{7/7}{}{0}}
|
||||
\headcommand {\beamer@framepages {7}{7}}
|
||||
\headcommand {\slideentry {0}{0}{8}{8/8}{}{0}}
|
||||
\headcommand {\beamer@framepages {8}{8}}
|
||||
\headcommand {\slideentry {0}{0}{9}{9/9}{}{0}}
|
||||
\headcommand {\beamer@framepages {9}{9}}
|
||||
\headcommand {\slideentry {0}{0}{10}{10/10}{}{0}}
|
||||
\headcommand {\beamer@framepages {10}{10}}
|
||||
\headcommand {\slideentry {0}{0}{11}{11/11}{}{0}}
|
||||
\headcommand {\beamer@framepages {11}{11}}
|
||||
\headcommand {\slideentry {0}{0}{12}{12/12}{}{0}}
|
||||
\headcommand {\beamer@framepages {12}{12}}
|
||||
\headcommand {\slideentry {0}{0}{13}{13/13}{}{0}}
|
||||
\headcommand {\beamer@framepages {13}{13}}
|
||||
\headcommand {\slideentry {0}{0}{14}{14/14}{}{0}}
|
||||
\headcommand {\beamer@framepages {14}{14}}
|
||||
\headcommand {\slideentry {0}{0}{15}{15/15}{}{0}}
|
||||
\headcommand {\beamer@framepages {15}{15}}
|
||||
\headcommand {\slideentry {0}{0}{16}{16/16}{}{0}}
|
||||
\headcommand {\beamer@framepages {16}{16}}
|
||||
\headcommand {\slideentry {0}{0}{17}{17/17}{}{0}}
|
||||
\headcommand {\beamer@framepages {17}{17}}
|
||||
\headcommand {\slideentry {0}{0}{18}{18/18}{}{0}}
|
||||
\headcommand {\beamer@framepages {18}{18}}
|
||||
\headcommand {\slideentry {0}{0}{19}{19/19}{}{0}}
|
||||
\headcommand {\beamer@framepages {19}{19}}
|
||||
\headcommand {\beamer@partpages {1}{19}}
|
||||
\headcommand {\beamer@subsectionpages {1}{19}}
|
||||
\headcommand {\beamer@sectionpages {1}{19}}
|
||||
\headcommand {\beamer@documentpages {19}}
|
||||
\headcommand {\gdef \inserttotalframenumber {19}}
|
|
@ -0,0 +1,39 @@
|
|||
\beamer@slide {Thesis@ls9<1>}{2}
|
||||
\beamer@slide {Thesis@ls9}{2}
|
||||
\beamer@slide {Today<1>}{3}
|
||||
\beamer@slide {Today}{3}
|
||||
\beamer@slide {Anomaly Detection<1>}{4}
|
||||
\beamer@slide {Anomaly Detection}{4}
|
||||
\beamer@slide {fig:prep03Anomaly_Detectioncirclepdf}{4}
|
||||
\beamer@slide {knn<1>}{5}
|
||||
\beamer@slide {knn}{5}
|
||||
\beamer@slide {Better knn<1>}{6}
|
||||
\beamer@slide {Better knn}{6}
|
||||
\beamer@slide {Comparison<1>}{7}
|
||||
\beamer@slide {Comparison}{7}
|
||||
\beamer@slide {What to do?<1>}{8}
|
||||
\beamer@slide {What to do?}{8}
|
||||
\beamer@slide {What to do?<1>}{9}
|
||||
\beamer@slide {What to do?}{9}
|
||||
\beamer@slide {Requirements<1>}{10}
|
||||
\beamer@slide {Requirements}{10}
|
||||
\beamer@slide {Normalising Flows<1>}{11}
|
||||
\beamer@slide {Normalising Flows}{11}
|
||||
\beamer@slide {Graph Normalising Flows<1>}{12}
|
||||
\beamer@slide {Graph Normalising Flows}{12}
|
||||
\beamer@slide {Graph Normalising Flows<1>}{13}
|
||||
\beamer@slide {Graph Normalising Flows}{13}
|
||||
\beamer@slide {Requirements<1>}{14}
|
||||
\beamer@slide {Requirements}{14}
|
||||
\beamer@slide {Old Thesis Sina<1>}{15}
|
||||
\beamer@slide {Old Thesis Sina}{15}
|
||||
\beamer@slide {fig:prep20Old_Thesis_SinaBildschirmfoto vom 2022-09-26 16-22-30png}{15}
|
||||
\beamer@slide {Old Thesis Britta<1>}{16}
|
||||
\beamer@slide {Old Thesis Britta}{16}
|
||||
\beamer@slide {fig:prep21Old_Thesis_BrittaBildschirmfoto vom 2022-09-26 16-23-26png}{16}
|
||||
\beamer@slide {Old Thesis Hsin Ping<1>}{17}
|
||||
\beamer@slide {Old Thesis Hsin Ping}{17}
|
||||
\beamer@slide {fig:prep22Old_Thesis_Hsin_PingBildschirmfoto vom 2022-09-26 16-24-14png}{17}
|
||||
\beamer@slide {Old Thesis Nikitha<1>}{18}
|
||||
\beamer@slide {Old Thesis Nikitha}{18}
|
||||
\beamer@slide {fig:prep23Old_Thesis_NikithaBildschirmfoto vom 2022-09-26 16-25-06png}{18}
|
|
@ -0,0 +1,585 @@
|
|||
\UseRawInputEncoding
|
||||
%\documentclass[hyperref={pdfpagelabels=false}]{beamer}
|
||||
\documentclass[hyperref={pdfpagelabels=false},aspectratio=169]{beamer}
|
||||
% Die Hyperref Option hyperref={pdfpagelabels=false} verhindert die Warnung:
|
||||
% Package hyperref Warning: Option `pdfpagelabels' is turned off
|
||||
% (hyperref) because \thepage is undefined.
|
||||
% Hyperref stopped early
|
||||
%
|
||||
|
||||
\usepackage{lmodern}
|
||||
% Das Paket lmodern erspart die folgenden Warnungen:
|
||||
% LaTeX Font Warning: Font shape `OT1/cmss/m/n' in size <4> not available
|
||||
% (Font) size <5> substituted on input line 22.
|
||||
% LaTeX Font Warning: Size substitutions with differences
|
||||
% (Font) up to 1.0pt have occurred.
|
||||
%
|
||||
|
||||
% Wenn \titel{\ldots} \author{\ldots} erst nach \begin{document} kommen,
|
||||
% kommt folgende Warnung:
|
||||
% Package hyperref Warning: Option `pdfauthor' has already been used,
|
||||
% (hyperref) ...
|
||||
% Daher steht es hier vor \begin{document}
|
||||
|
||||
\title[Thesis Simon]{Open Thesis Topics}
|
||||
\author{Simon.Kluettermann@cs.tu-dortmund.de}
|
||||
\date{\today}
|
||||
|
||||
|
||||
\institute{ls9 tu Dortmund}
|
||||
|
||||
|
||||
% Dadurch wird verhindert, dass die Navigationsleiste angezeigt wird.
|
||||
\setbeamertemplate{navigation symbols}{}
|
||||
|
||||
% zusaetzlich ist das usepackage{beamerthemeshadow} eingebunden
|
||||
\usepackage{beamerthemeshadow}
|
||||
|
||||
\hypersetup{pdfstartview={Fit}} % fits the presentation to the window when first displayed
|
||||
|
||||
\usepackage{appendixnumberbeamer}
|
||||
\usepackage{listings}
|
||||
|
||||
|
||||
\usetheme{CambridgeUS}
|
||||
\usepackage{ngerman}
|
||||
\usecolortheme{dolphin}
|
||||
|
||||
|
||||
% \beamersetuncovermixins{\opaqueness<1>{25}}{\opaqueness<2$\Rightarrow${15}}
|
||||
% sorgt dafuer das die Elemente die erst noch (zukuenftig) kommen
|
||||
% nur schwach angedeutet erscheinen
|
||||
%\beamersetuncovermixins{\opaqueness<1>{25}}{\opaqueness<2$\Rightarrow${15}}%here disabled
|
||||
% klappt auch bei Tabellen, wenn teTeX verwendet wird\ldots
|
||||
\renewcommand{\figurename}{}
|
||||
|
||||
\setbeamertemplate{footline}
|
||||
{
|
||||
\leavevmode%
|
||||
\hbox{%
|
||||
\begin{beamercolorbox}[wd=.4\paperwidth,ht=2.25ex,dp=1ex,center]{author in head/foot}%
|
||||
\usebeamerfont{author in head/foot}\insertshorttitle
|
||||
\end{beamercolorbox}%
|
||||
\begin{beamercolorbox}[wd=.25\paperwidth,ht=2.25ex,dp=1ex,center]{title in head/foot}%
|
||||
\usebeamerfont{title in head/foot}\insertsection
|
||||
\end{beamercolorbox}%
|
||||
\begin{beamercolorbox}[wd=.3499\paperwidth,ht=2.25ex,dp=1ex,right]{date in head/foot}%
|
||||
\usebeamerfont{date in head/foot}\insertshortdate{}\hspace*{2em}
|
||||
\hyperlink{toc}{\insertframenumber{} / \inserttotalframenumber\hspace*{2ex}}
|
||||
\end{beamercolorbox}}%
|
||||
\vskip0pt%
|
||||
}
|
||||
|
||||
\usepackage[absolute,overlay]{textpos}
|
||||
\usepackage{graphicx}
|
||||
|
||||
\newcommand{\source}[1]{\begin{textblock*}{9cm}(0.1cm,8.9cm)
|
||||
\begin{beamercolorbox}[ht=0.5cm,left]{framesource}
|
||||
\usebeamerfont{framesource}\usebeamercolor[fg!66]{framesource} Source: {#1}
|
||||
\end{beamercolorbox}
|
||||
\end{textblock*}}
|
||||
|
||||
|
||||
\begin{document}
|
||||
|
||||
|
||||
|
||||
%from file ../knn1//data/000.txt
|
||||
\begin{frame}[label=]
|
||||
\frametitle{}
|
||||
\begin{titlepage}
|
||||
|
||||
\centering
|
||||
{\huge\bfseries \par}
|
||||
\vspace{2cm}
|
||||
{\LARGE\itshape Simon Kluettermann\par}
|
||||
\vspace{1.5cm}
|
||||
{\scshape\Large Master Thesis in Physics\par}
|
||||
\vspace{0.2cm}
|
||||
{\Large submitted to the \par}
|
||||
\vspace{0.2cm}
|
||||
{\scshape\Large Faculty of Mathematics Computer Science and Natural Sciences \par}
|
||||
\vspace{0.2cm}
|
||||
{\Large \par}
|
||||
\vspace{0.2cm}
|
||||
{\scshape\Large RWTH Aachen University}
|
||||
\vspace{1cm}
|
||||
|
||||
\vfill
|
||||
{\scshape\Large Department of Physics\par}
|
||||
\vspace{0.2cm}
|
||||
{\scshape\Large Insitute for theoretical Particle Physics and Cosmology\par}
|
||||
\vspace{0.2cm}
|
||||
{ \Large\par}
|
||||
\vspace{0.2cm}
|
||||
{\Large First Referee: Prof. Dr. Michael Kraemer \par}
|
||||
{\Large Second Referee: Prof. Dr. Felix Kahlhoefer}
|
||||
|
||||
\vfill
|
||||
|
||||
% Bottom of the page
|
||||
{\large November 2020 \par}
|
||||
\end{titlepage}
|
||||
\pagenumbering{roman}
|
||||
\thispagestyle{empty}
|
||||
\null
|
||||
\newpage
|
||||
\setcounter{page}{1}
|
||||
\pagenumbering{arabic}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/001Thesis@ls9.txt
|
||||
\begin{frame}[label=Thesis@ls9]
|
||||
\frametitle{Thesis@ls9}
|
||||
\begin{itemize}
|
||||
|
||||
\item First: Find a topic and a supervisor
|
||||
|
||||
\item Work one month on this, to make sure
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item you still like your topic
|
||||
|
||||
\item and you are sure you can handle the topic
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\item then short presentation in front of our chair (15min, relaxed)
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item get some feedback/suggestions
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\item afterwards register the thesis
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item (different for CS/DS students)
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\item Problem: We are not able to supervise more than 2 students at the same time (CS faculty rules)
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/002Today.txt
|
||||
\begin{frame}[label=Today]
|
||||
\frametitle{Today}
|
||||
\begin{itemize}
|
||||
|
||||
\item First: A short summary of each Topic
|
||||
|
||||
\item Then time for questions/Talk with your supervisor about each topic that sounds interesting
|
||||
|
||||
\item Your own topics are always welcome;)
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/003Anomaly Detection.txt
|
||||
\begin{frame}[label=Anomaly Detection]
|
||||
\frametitle{Anomaly Detection}
|
||||
\begin{columns}[c] % align columns
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{itemize}
|
||||
|
||||
\item Im working on Anomaly Detection
|
||||
|
||||
\item That means characterising an often very complex distributions, to find events that dont match the expected distribution
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.9\textwidth]{../prep/03Anomaly_Detection/circle.pdf}
|
||||
\label{fig:prep03Anomaly_Detectioncirclepdf}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\end{columns}
|
||||
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/004knn.txt
|
||||
\begin{frame}[label=knn]
|
||||
\frametitle{knn}
|
||||
\begin{itemize}
|
||||
|
||||
\item kNN algorithm can also be used for AD
|
||||
|
||||
\item if the k closest point is further away, a sample is considered more anomalous
|
||||
|
||||
\item $r=\frac{k}{2N\cdot pdf}$
|
||||
|
||||
\item Powerful method, as it can model the pdf directly
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/005Better knn.txt
|
||||
\begin{frame}[label=Better knn]
|
||||
\frametitle{Better knn}
|
||||
\begin{itemize}
|
||||
|
||||
\item The model (mostly) ignores every known sample except one
|
||||
|
||||
\item So there are extensions
|
||||
|
||||
\item $avg=\frac{1}{N} \sum_i knn_i(x)$
|
||||
|
||||
\item $wavg=\frac{1}{N} \sum_i \frac{knn_i(x)}{i}$
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/006Comparison.txt
|
||||
\begin{frame}[label=Comparison]
|
||||
%\frametitle{Comparison}
|
||||
|
||||
|
||||
\begin{tabular}{llllll}
|
||||
\hline
|
||||
Dataset & wavg & avg & 1 & 3 & 5 \\
|
||||
\hline
|
||||
$vertebral$ & $\textbf{0.4506}$ & $\textbf{0.4506}$ & $\textbf{0.4667}$ & $\textbf{0.4667}$ & $\textbf{0.45}$ \\
|
||||
... & & & & & \\
|
||||
$thyroid$ & $\textbf{0.9138}$ & $\textbf{0.9151}$ & $\textbf{0.8763}$ & $\textbf{0.9086}$ & $\textbf{0.914}$ \\
|
||||
$Iris\_setosa$ & $\textbf{0.9333}$ & $\textbf{0.9333}$ & $\textbf{0.9333}$ & $\textbf{0.9}$ & $\textbf{0.9}$ \\
|
||||
$breastw$ & $\textbf{0.9361}$ & $\textbf{0.9361}$ & $\textbf{0.9211}$ & $\textbf{0.9248}$ & $\textbf{0.9286}$ \\
|
||||
$wine$ & $\textbf{0.95}$ & $\textbf{0.95}$ & $\textbf{0.9}$ & $\textbf{0.95}$ & $\textbf{0.95}$ \\
|
||||
$pendigits$ & $\textbf{0.9487}$ & $\textbf{0.9487}$ & $\textbf{0.9391}$ & $\textbf{0.9295}$ & $\textbf{0.9359}$ \\
|
||||
$segment$ & $\textbf{0.9747}$ & $\textbf{0.9747}$ & $\textbf{0.9495}$ & $\textbf{0.9545}$ & $\textbf{0.9394}$ \\
|
||||
$banknote-authentication$ & $\textbf{0.9777}$ & $\textbf{0.9776}$ & $\textbf{0.9408}$ & $\textbf{0.943}$ & $\textbf{0.9583}$ \\
|
||||
$vowels$ & $\textbf{0.9998}$ & $\textbf{0.9972}$ & $\textbf{0.99}$ & $\textbf{0.92}$ & $\textbf{0.93}$ \\
|
||||
$Ecoli$ & $\textbf{1.0}$ & $\textbf{1.0}$ & $\textbf{0.9}$ & $\textbf{1.0}$ & $\textbf{1.0}$ \\
|
||||
$$ & $$ & $$ & $$ & $$ & $$ \\
|
||||
$Average$ & $\textbf{0.7528} $ & $\textbf{0.7520} $ & $0.7325 $ & $0.7229 $ & $0.7157 $ \\
|
||||
\hline
|
||||
\end{tabular}
|
||||
|
||||
|
||||
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/007What to do?.txt
|
||||
\begin{frame}[label=What to do?]
|
||||
\frametitle{What to do?}
|
||||
\begin{itemize}
|
||||
|
||||
\item Evaluation as anomaly detector is complicated
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item Requires known anomalies
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\item $\Rightarrow$So evaluate as density estimator
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item Does not require anomalies
|
||||
|
||||
\item Allows generating infinite amounts of training data
|
||||
|
||||
|
||||
\end{itemize}
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/008What to do?.txt
|
||||
\begin{frame}[label=What to do?]
|
||||
\frametitle{What to do?}
|
||||
\begin{itemize}
|
||||
|
||||
\item Collect Extensions of the oc-knn algorithm
|
||||
|
||||
\item Define some distance measure to a known pdf
|
||||
|
||||
\item Generate random datapoints following the pdf
|
||||
|
||||
\item Evaluate which algorithm finds the pdf the best
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/009Requirements.txt
|
||||
\begin{frame}[label=Requirements]
|
||||
\frametitle{Requirements}
|
||||
\begin{itemize}
|
||||
|
||||
\item Knowledge of python ( sum([i for i in range(5) if i\%2]) )
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item Ideally incl numpy
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\item Basic university level Math (you could argue that $r_k \propto \frac{k}{pdf}$)
|
||||
|
||||
\item Ideally some experience working on a ssh server
|
||||
|
||||
\item $\Rightarrow$Good as a Bachelor Thesis
|
||||
|
||||
\item For a Master Thesis, I would extend this a bit (Could you also find $k$?)
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/010Normalising Flows.txt
|
||||
\begin{frame}[label=Normalising Flows]
|
||||
\frametitle{Normalising Flows}
|
||||
\begin{itemize}
|
||||
|
||||
\item Deep Learning Method, in which the output is normalised
|
||||
|
||||
\item $\int f(x) dx=1 \; \forall f(x)$
|
||||
|
||||
\item Can be used to estimate probability density functions
|
||||
|
||||
\item $\Rightarrow$Thus useful for AD
|
||||
|
||||
\item $\int f(h(x)) \|\frac{\delta x}{\delta h}\| dh=1 \; \forall h(x)$
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/011Graph Normalising Flows.txt
|
||||
\begin{frame}[label=Graph Normalising Flows]
|
||||
\frametitle{Graph Normalising Flows}
|
||||
\begin{itemize}
|
||||
|
||||
\item How to apply this to graphs?
|
||||
|
||||
\item One Paper (Liu 2019) uses two NN:
|
||||
|
||||
\item Autoencoder graph$\Rightarrow$vector
|
||||
|
||||
\item NF on vector data
|
||||
|
||||
\item which is fine, but also not really graph specific
|
||||
|
||||
\item No interaction between encoding and transformation
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/012Graph Normalising Flows.txt
|
||||
\begin{frame}[label=Graph Normalising Flows]
|
||||
\frametitle{Graph Normalising Flows}
|
||||
\begin{itemize}
|
||||
|
||||
\item So why not do this directly?
|
||||
|
||||
\item $\Rightarrow$Requires differentiating a graph
|
||||
|
||||
\item Why not use only one Network?
|
||||
|
||||
\item Graph$\Rightarrow$Vector$\Rightarrow$pdf
|
||||
|
||||
\item $\Rightarrow$Finds trivial solution, as $<pdf> \propto \frac{1}{\sigma_{Vector}}$
|
||||
|
||||
\item So regularise the standart deviation of the vector space!
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item Interplay between encoding and NF
|
||||
|
||||
\item Could also be useful for highdim data
|
||||
|
||||
|
||||
\end{itemize}
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/013Requirements.txt
|
||||
\begin{frame}[label=Requirements]
|
||||
\frametitle{Requirements}
|
||||
\begin{itemize}
|
||||
|
||||
\item Proficient in python ( [i for i in range(1,N) if not [j for j in range(2,i) if not i\%j]] )
|
||||
|
||||
\begin{itemize}
|
||||
|
||||
\item Ideally incl numpy, tensorflow, keras
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\item Some deep learning experience
|
||||
|
||||
\item University level math (google Cholesky Decomposition. Why is this useful for NF?)
|
||||
|
||||
\item Ideally some experience working on a ssh server
|
||||
|
||||
\item A bit more challenging$\Rightarrow$Better as a Master thesis
|
||||
|
||||
\item (Still we would start very slowly of course)
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/014Old Thesis Sina.txt
|
||||
\begin{frame}[label=Old Thesis Sina]
|
||||
\frametitle{Sina}
|
||||
\begin{columns}[c] % align columns
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{itemize}
|
||||
|
||||
\item Isolation Forest: Different Anomaly Detection Algorithm
|
||||
|
||||
\item Problem: Isolation Forests dont work on categorical data
|
||||
|
||||
\item $\Rightarrow$Extend them to categorical data
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.9\textwidth]{../prep/20Old_Thesis_Sina/Bildschirmfoto vom 2022-09-26 16-22-30.png}
|
||||
\label{fig:prep20Old_Thesis_SinaBildschirmfoto vom 2022-09-26 16-22-30png}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\end{columns}
|
||||
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/015Old Thesis Britta.txt
|
||||
\begin{frame}[label=Old Thesis Britta]
|
||||
\frametitle{Britta}
|
||||
\begin{columns}[c] % align columns
|
||||
\begin{column}{0.58\textwidth}%.48
|
||||
\begin{itemize}
|
||||
|
||||
\item Reidentification: Find known objects in new images
|
||||
|
||||
\item Task: Find if two images of pallet blocks are of the same pallet block
|
||||
|
||||
\item Use AD to represent the pallet blocks
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\begin{column}{0.38\textwidth}%.48
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.9\textwidth]{../prep/21Old_Thesis_Britta/Bildschirmfoto vom 2022-09-26 16-23-26.png}
|
||||
\label{fig:prep21Old_Thesis_BrittaBildschirmfoto vom 2022-09-26 16-23-26png}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\end{columns}
|
||||
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/016Old Thesis Hsin Ping.txt
|
||||
\begin{frame}[label=Old Thesis Hsin Ping]
|
||||
\frametitle{Hsin Ping}
|
||||
\begin{columns}[c] % align columns
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{itemize}
|
||||
|
||||
\item Ensemble: Combination of multiple models
|
||||
|
||||
\item Task: Explain the prediction of a model using the ensemble structure
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.9\textwidth]{../prep/22Old_Thesis_Hsin_Ping/Bildschirmfoto vom 2022-09-26 16-24-14.png}
|
||||
\label{fig:prep22Old_Thesis_Hsin_PingBildschirmfoto vom 2022-09-26 16-24-14png}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\end{columns}
|
||||
|
||||
\end{frame}
|
||||
|
||||
|
||||
%from file ../knn1//data/017Old Thesis Nikitha.txt
|
||||
\begin{frame}[label=Old Thesis Nikitha]
|
||||
\frametitle{Nikitha}
|
||||
\begin{columns}[c] % align columns
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{itemize}
|
||||
|
||||
\item Task: Explore a new kind of ensemble
|
||||
|
||||
\item Instead of many uncorrelated models, let the models interact during training
|
||||
|
||||
|
||||
\end{itemize}
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\begin{column}{0.48\textwidth}%.48
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.9\textwidth]{../prep/23Old_Thesis_Nikitha/Bildschirmfoto vom 2022-09-26 16-25-06.png}
|
||||
\label{fig:prep23Old_Thesis_NikithaBildschirmfoto vom 2022-09-26 16-25-06png}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\end{column}%
|
||||
\hfill%
|
||||
\end{columns}
|
||||
|
||||
\end{frame}
|
||||
|
||||
\begin{frame}
|
||||
Questions?
|
||||
\end{frame}
|
||||
|
||||
|
||||
|
||||
\end{document}
|
|
@ -0,0 +1 @@
|
|||
<titlepage>
|
|
@ -0,0 +1,15 @@
|
|||
First: Find a topic and a supervisor
|
||||
Work one month on this, to make sure
|
||||
<l2st>
|
||||
you still like your topic
|
||||
and you are sure you can handle the topic
|
||||
</l2st>
|
||||
then short presentation in front of our chair (15min, relaxed)
|
||||
<l2st>
|
||||
get some feedback/suggestions
|
||||
</l2st>
|
||||
afterwards register the thesis
|
||||
<l2st>
|
||||
(different for CS/DS students)
|
||||
</l2st>
|
||||
Problem: We are not able to supervise more than 2 students at the same time (CS faculty rules)
|
|
@ -0,0 +1,3 @@
|
|||
First: A short summary of each Topic
|
||||
Then time for questions/Talk with your supervisor about each topic that sounds interesting
|
||||
Your own topics are always welcome;)
|
|
@ -0,0 +1,2 @@
|
|||
Im working on Anomaly Detection
|
||||
That means characterising an often very complex distributions, to find events that dont match the expected distribution
|
|
@ -0,0 +1,4 @@
|
|||
kNN algorithm can also be used for AD
|
||||
if the k closest point is further away, a sample is considered more anomalous
|
||||
$r=\frac{k}{2N\cdot pdf}$
|
||||
Powerful method, as it can model the pdf directly
|
|
@ -0,0 +1,5 @@
|
|||
The model (mostly) ignores every known sample except one
|
||||
So there are extensions
|
||||
$avg=\frac{1}{N} \sum_i knn_i(x)$
|
||||
$wavg=\frac{1}{N} \sum_i \frac{knn_i(x)}{i}$
|
||||
|
|
@ -0,0 +1 @@
|
|||
nothing
|
|
@ -0,0 +1,9 @@
|
|||
Evaluation as anomaly detector is complicated
|
||||
<l2st>
|
||||
Requires known anomalies
|
||||
</l2st>
|
||||
->So evaluate as density estimator
|
||||
<l2st>
|
||||
Does not require anomalies
|
||||
Allows generating infinite amounts of training data
|
||||
</l2st>
|
|
@ -0,0 +1,4 @@
|
|||
Collect Extensions of the oc-knn algorithm
|
||||
Define some distance measure to a known pdf
|
||||
Generate random datapoints following the pdf
|
||||
Evaluate which algorithm finds the pdf the best
|
|
@ -0,0 +1,8 @@
|
|||
Knowledge of python ( sum([i for i in range(5) if i\%2]) )
|
||||
<l2st>
|
||||
Ideally incl numpy
|
||||
</l2st>
|
||||
Basic university level Math (you could argue that $r_k \propto \frac{k}{pdf}$)
|
||||
Ideally some experience working on a ssh server
|
||||
->Good as a Bachelor Thesis
|
||||
For a Master Thesis, I would extend this a bit (Could you also find $k$?)
|
|
@ -0,0 +1,5 @@
|
|||
Deep Learning Method, in which the output is normalised
|
||||
$\int f(x) dx=1 \; \forall f(x)$
|
||||
Can be used to estimate probability density functions
|
||||
->Thus useful for AD
|
||||
$\int f(h(x)) \|\frac{\delta h}{\delta x}\| dx=1 \; \forall h(x)$
|
|
@ -0,0 +1,6 @@
|
|||
How to apply this to graphs?
|
||||
One Paper (Liu 2019) uses two NN:
|
||||
Autoencoder graph->vector
|
||||
NF on vector data
|
||||
which is fine, but also not really graph specific
|
||||
No interaction between encoding and transformation
|
|
@ -0,0 +1,10 @@
|
|||
So why not do this directly?
|
||||
->Requires differentiating a graph
|
||||
Why not use only one Network?
|
||||
Graph->Vector->pdf
|
||||
->Finds trivial solution, as $<pdf> \propto \frac{1}{\sigma_{Vector}}$
|
||||
So regularise the standart deviation of the vector space!
|
||||
<l2st>
|
||||
Interplay between encoding and NF
|
||||
Could also be useful for highdim data
|
||||
</l2st>
|
|
@ -0,0 +1,9 @@
|
|||
Proficient in python ( [i for i in range(1,N) if not [j for j in range(2,i) if not i\%j]] )
|
||||
<l2st>
|
||||
Ideally incl numpy, tensorflow, keras
|
||||
</l2st>
|
||||
Some deep learning experience
|
||||
University level math (google Cholesky Decomposition. Why is this useful for NF?)
|
||||
Ideally some experience working on a ssh server
|
||||
A bit more challenging->Better as a Master thesis
|
||||
(Still we would start very slowly of course)
|
After Width: | Height: | Size: 18 KiB |
|
@ -0,0 +1,3 @@
|
|||
Isolation Forest: Different Anomaly Detection Algorithm
|
||||
Problem: Isolation Forests dont work on categorical data
|
||||
->Extend them to categorical data
|
After Width: | Height: | Size: 979 KiB |
|
@ -0,0 +1,3 @@
|
|||
Reidentification: Find known objects in new images
|
||||
Task: Find if two images of pallet blocks are of the same pallet block
|
||||
Use AD to represent the pallet blocks
|
After Width: | Height: | Size: 43 KiB |
|
@ -0,0 +1,2 @@
|
|||
Ensemble: Combination of multiple models
|
||||
Task: Explain the prediction of a model using the ensemble structure
|
After Width: | Height: | Size: 47 KiB |
|
@ -0,0 +1,2 @@
|
|||
Task: Explore a new kind of ensemble
|
||||
Instead of many uncorrelated models, let the models interact during training
|
After Width: | Height: | Size: 20 KiB |
After Width: | Height: | Size: 989 KiB |
After Width: | Height: | Size: 265 KiB |