zenon/master-thesis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix punctuation and missing word

Browse Source
This commit is contained in:
Tobias Eidelpes 2023-11-22 10:58:57 +01:00
parent 58ea85fc4d
commit d79f968c6f
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
thesis/thesis.tex
View File

@ -443,8 +443,8 @@ game. The tasks in $T$ are playing the game multiple times, and the
experience $E$ is gained by letting the program play the game against experience $E$ is gained by letting the program play the game against
itself. itself.
Machine learning is thought to be a sub-field of \gls{ai}. \gls{ai} a Machine learning is thought to be a sub-field of \gls{ai}. \gls{ai} is
more general term for the scientific endeavour of creating things a more general term for the scientific endeavour of creating things
which possess the kind of intelligence we humans have. Since those which possess the kind of intelligence we humans have. Since those
things will not have been created \emph{naturally}, their intelligence things will not have been created \emph{naturally}, their intelligence
is termed \emph{artificial}. Within the field of \gls{ai} there have is termed \emph{artificial}. Within the field of \gls{ai} there have
@ -1027,10 +1027,10 @@ section~\ref{sssec:obj-dpm}. However, the authors showed that
their processing performance is not yet up to par with traditional their processing performance is not yet up to par with traditional
methods. Furthermore, R-\gls{cnn} crushes \glspl{dpm} on the \gls{voc} methods. Furthermore, R-\gls{cnn} crushes \glspl{dpm} on the \gls{voc}
2007 challenge with a \gls{map} of 58.5\% \cite{girshick2014} versus 2007 challenge with a \gls{map} of 58.5\% \cite{girshick2014} versus
33.7\% (\gls{dpm}-v5 \cite{girshick,felzenszwalb2010}) This was enough 33.7\% (\gls{dpm}-v5 \cite{girshick,felzenszwalb2010}). This was
to spark renewed interest in \glspl{cnn} and—with better availability enough to spark renewed interest in \glspl{cnn} and—with better
of large data sets and \gls{gpu} processing capabilities—opened the availability of large data sets and \gls{gpu} processing
way for further research in that direction. capabilities—opened the way for further research in that direction.
\subsubsection{SPP-net} \subsubsection{SPP-net}
\label{sssec:theory-spp-net} \label{sssec:theory-spp-net}