You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
38 lines
2.3 KiB
Plaintext
38 lines
2.3 KiB
Plaintext
4 years ago
|
|
||
|
|
\boolfalse {citerequest}\boolfalse {citetracker}\boolfalse {pagetracker}\boolfalse {backtracker}\relax
|
||
|
|
\babel@toc {english}{}
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {2.1}{\ignorespaces Illustration of a neural network}}{2}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {2.2}{\ignorespaces Plots of the activation functions\relax }}{4}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {2.3}{\ignorespaces Structure of a single neuron\relax }}{4}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {3.1}{\ignorespaces Overfitting of shallow neural networks}}{10}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {3.2}{\ignorespaces Comparison of shallow neural networks and regression splines}}{21}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.1}{\ignorespaces Signal smoothing using convolution}}{23}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.2}{\ignorespaces Channel separation of color image}}{24}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.3}{\ignorespaces Convolution applied on image}}{25}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.4}{\ignorespaces MNIST data set}}{29}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.5}{\ignorespaces architecture\relax }}{29}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.6}{\ignorespaces Performance comparison of SDG and GD}}{30}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.7}{\ignorespaces Performance comparison of training algorithms}}{35}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.8}{\ignorespaces Image data generation}}{37}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.9}{\ignorespaces Performance comparison of overfitting measures}}{38}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.10}{\ignorespaces Fashion MNIST data set}}{39}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.11}{\ignorespaces \relax }}{41}%
|
||
|
|
\defcounter {refsection}{0}\relax
|
||
|
|
\contentsline {figure}{\numberline {4.12}{\ignorespaces Sample pictures of the mnist fashioyn dataset, one per class.\relax }}{41}%
|