mirror of
https://github.com/MartinThoma/LaTeX-examples.git
synced 2025-04-25 06:18:05 +02:00
Analyse hinzugefügt
This commit is contained in:
parent
32aedc66cc
commit
04a45f295e
4 changed files with 77 additions and 0 deletions
27
documents/DYCOS/Analyse.tex
Normal file
27
documents/DYCOS/Analyse.tex
Normal file
|
@ -0,0 +1,27 @@
|
||||||
|
Für den DYCOS-Algorithmus wurde in \cite{aggarwal2011} bewiesen,
|
||||||
|
dass sich nach Ausführung von DYCOS für einen unbeschrifteten
|
||||||
|
Knoten mit einer Wahrscheinlichkeit von höchstens
|
||||||
|
$(1-k)\cdot e^{-l \cdot b^2 / 2}$ eine Knotenbeschriftung ergibt, deren
|
||||||
|
relative Häufigkeit weniger als $b$ der häufigsten Beschriftung ist.
|
||||||
|
Dabei ist $k$ die Anzahl der Klassen und $l$ die Länge der
|
||||||
|
Random-Walks.
|
||||||
|
|
||||||
|
Außerdem wurde experimentell anhand des DBLP-Datensatzes\footnote{http://dblp.uni-trier.de/}
|
||||||
|
und des CORA-Datensatzes\footnote{http://people.cs.umass.edu/~mccallum/data/cora-classify.tar.gz}
|
||||||
|
gezeigt, dass die Klassifikationsgüte nicht wesentlich von der
|
||||||
|
maximalen Listenlänge $a$ und der Anzahl der Wörter mit
|
||||||
|
höchstem Gini-Koeffizient $m$ abhängt. Obwohl es sich nicht sagen lässt,
|
||||||
|
wie genau die Ergebnisse aus \cite{aggarwal2011} zustande gekommen sind,
|
||||||
|
eignet sich das Kreuzvalidierungsverfahren zur Bestimmung der Klassifikationsgüte
|
||||||
|
wie es in \cite{Lavesson,Stone1974} vorgestellt wird:
|
||||||
|
\begin{enumerate}
|
||||||
|
\item Betrachte nur $V_{L,T}$.
|
||||||
|
\item Unterteile $V_{L,T}$ zufällig in $k$ disjunkte Mengen $M_1, \dots, M_k$.
|
||||||
|
\item \label{schritt3} Teste die Klassifikationsgüte, wenn die Knotenbeschriftungen
|
||||||
|
aller Knoten in $M_i$ für DYCOS verborgen werden für $i=1,\dots, k$.
|
||||||
|
\item Bilde den Durchschnitt der Klassifikationsgüten aus \cref{schritt3}.
|
||||||
|
\end{enumerate}
|
||||||
|
|
||||||
|
Es wird $k=10$ vorgeschlagen.
|
||||||
|
|
||||||
|
|
Binary file not shown.
|
@ -63,6 +63,9 @@
|
||||||
\section{DYCOS}
|
\section{DYCOS}
|
||||||
\input{DYCOS-Algorithmus}
|
\input{DYCOS-Algorithmus}
|
||||||
|
|
||||||
|
\section{Analyse des DYCOS-Algorithmus}
|
||||||
|
\input{Analyse}
|
||||||
|
|
||||||
\section{Probleme des DYCOS-Algorithmus}
|
\section{Probleme des DYCOS-Algorithmus}
|
||||||
\input{SchwaechenVerbesserungen}
|
\input{SchwaechenVerbesserungen}
|
||||||
|
|
||||||
|
|
|
@ -97,6 +97,51 @@
|
||||||
address = {New York, NY, USA},
|
address = {New York, NY, USA},
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@MASTERSTHESIS{heck,
|
||||||
|
AUTHOR = {Heck, Michael},
|
||||||
|
TITLE = {Unsupervised Acoustic Model Training for Simultaneous Lecture Translation in Incremental and Batch Mode},
|
||||||
|
SCHOOL = {Karlsruhe Institute of Technology},
|
||||||
|
TYPE = {Diploma Thesis},
|
||||||
|
ADDRESS = {Germany},
|
||||||
|
MONTH = DEC,
|
||||||
|
YEAR = 2012,
|
||||||
|
PDF = {http://isl.anthropomatik.kit.edu/cmu-kit/downloads/Diplomarbeit_Heck_Michael.pdf}
|
||||||
|
}
|
||||||
|
|
||||||
|
@MASTERSTHESIS{Lavesson,
|
||||||
|
AUTHOR = {Lavesson, Niklas},
|
||||||
|
TITLE = {Evaluation and analysis of supervised learning algorithms and classifiers},
|
||||||
|
SCHOOL = {Blekinge Institute of Technology},
|
||||||
|
TYPE = {Diploma Thesis},
|
||||||
|
ADDRESS = {Sweden},
|
||||||
|
MONTH = DEC,
|
||||||
|
YEAR = 2006,
|
||||||
|
PDF = {http://www.bth.se/fou/Forskinfo.nsf/Sok/c655a0b1f9f88d16c125714c00355e5d/$file/Lavesson_lic.pdf}
|
||||||
|
}
|
||||||
|
|
||||||
|
@article{Stone1974,
|
||||||
|
abstract = {{A generalized form of the cross-validation criterion is applied to the choice and assessment of prediction using the data-analytic concept of a prescri
|
||||||
|
ption. The examples used to illustrate the application are drawn from the problem areas of univariate estimation, linear regression and analysis of variance.}},
|
||||||
|
author = {Stone, M.},
|
||||||
|
citeulike-article-id = {6758792},
|
||||||
|
citeulike-linkout-0 = {http://dx.doi.org/10.2307/2984809},
|
||||||
|
citeulike-linkout-1 = {http://www.jstor.org/stable/2984809},
|
||||||
|
doi = {10.2307/2984809},
|
||||||
|
issn = {00359246},
|
||||||
|
journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
|
||||||
|
keywords = {biomarker, cross\_validation},
|
||||||
|
number = {2},
|
||||||
|
pages = {111--147},
|
||||||
|
posted-at = {2011-08-02 14:22:37},
|
||||||
|
priority = {2},
|
||||||
|
publisher = {Blackwell Publishing for the Royal Statistical Society},
|
||||||
|
title = {{Cross-Validatory Choice and Assessment of Statistical Predictions}},
|
||||||
|
url = {http://dx.doi.org/10.2307/2984809},
|
||||||
|
volume = {36},
|
||||||
|
year = {1974}
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
@incollection{porter,
|
@incollection{porter,
|
||||||
author = {Porter, M. F.},
|
author = {Porter, M. F.},
|
||||||
chapter = {An Algorithm for Suffix Stripping},
|
chapter = {An Algorithm for Suffix Stripping},
|
||||||
|
@ -112,6 +157,8 @@
|
||||||
address = {San Francisco, CA, USA},
|
address = {San Francisco, CA, USA},
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
@incollection{szummer,
|
@incollection{szummer,
|
||||||
title = {Partially labeled classification with Markov random walks},
|
title = {Partially labeled classification with Markov random walks},
|
||||||
author = {Martin Szummer and Jaakkola, Tommi},
|
author = {Martin Szummer and Jaakkola, Tommi},
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue