tri11paragon
/
COSC-4P80-Final-Project
mirror of https://github.com/tri11paragon/COSC-4P80-Final-Project.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

latex

Brett 2025-01-10 01:55:21 -05:00
parent 99622d8371
commit 749ca36310
13 changed files with 581 additions and 431 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CMakeLists.txt
View File

@ -1,5 +1,5 @@
cmake_minimum_required(VERSION 3.25)
project(COSC-4P80-Final-Project VERSION 0.0.28)
project(COSC-4P80-Final-Project VERSION 0.0.29)
option(ENABLE_ADDRSAN "Enable the address sanitizer" OFF)
option(ENABLE_UBSAN "Enable the ub sanitizer" OFF)

8
latex/chapters/conclusion.aux
View File

@ -2,7 +2,7 @@
\providecommand{\transparent@use}[1]{}
\providecommand\hyper@newdestlabel[2]{}
\@setckpt{chapters/conclusion}{
\setcounter{page}{3}
\setcounter{page}{6}
\setcounter{equation}{0}
\setcounter{enumi}{0}
\setcounter{enumii}{0}
@ -11,8 +11,8 @@
\setcounter{footnote}{0}
\setcounter{mpfootnote}{0}
\setcounter{part}{0}
\setcounter{chapter}{2}
\setcounter{section}{2}
\setcounter{chapter}{3}
\setcounter{section}{0}
\setcounter{subsection}{0}
\setcounter{subsubsection}{0}
\setcounter{paragraph}{0}
@ -40,5 +40,5 @@
\setcounter{section@level}{4}
\setcounter{Item}{0}
\setcounter{Hfootnote}{0}
\setcounter{bookmark@seq@number}{5}
\setcounter{bookmark@seq@number}{6}
}

2
latex/chapters/conclusion.tex
View File

@ -0,0 +1,2 @@
mention paramter counts being unequal and that provides more options for storing information
mention that parameter counts being the same doesn't account for differences in "power" of functions.

7
latex/chapters/introduction_and_motivation.aux
View File

@ -11,12 +11,13 @@
\@writefile{lof}{\addvspace {10\p@ }}
\@writefile{lot}{\addvspace {10\p@ }}
\@writefile{toc}{\contentsline {paragraph}{}{2}{section*.7}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {2.1}Experiment 1}{2}{section.2.1}\protected@file@percent }
\@writefile{toc}{\contentsline {paragraph}{}{2}{section*.8}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {2.2}Experiment 2}{2}{section.2.2}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {2.1}Experiment 1}{2}{section.2.1}\protected@file@percent }
\@writefile{toc}{\contentsline {paragraph}{}{2}{section*.9}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {2.2}Experiment 2}{3}{section.2.2}\protected@file@percent }
\@writefile{toc}{\contentsline {paragraph}{}{3}{section*.10}\protected@file@percent }
\@setckpt{chapters/introduction_and_motivation}{
\setcounter{page}{3}
\setcounter{page}{4}
\setcounter{equation}{0}
\setcounter{enumi}{0}
\setcounter{enumii}{0}

8
latex/chapters/introduction_and_motivation.tex
View File

@ -6,12 +6,16 @@
\paragraph{}The MNIST database is a standard benchmark for image-processing neural networks. For our comparison, we will use a modified version of the DLIB deep learning example. This approach allows us to showcase the differences between standard feed-forward neural networks and deep learning networks without requiring expensive GPUs or AI accelerators. While the MNIST dataset is solvable using feed-forward neural networks, we intend to demonstrate that deep learning can achieve better classification performance, even on smaller networks.
\chapter{Experimental Setup}
\paragraph{}
The MNIST database consists of gray-scale images sized 28x28 with 60k training images and 10k test images. For each experiment we will present graphs of the average error per epoch compared between both configurations alongside a table of test results on the final network after training. Due to resource constraints training is limited to at most 100 epochs and our experiments are averaged over ten runs (the deep learning configuration takes 6 hours to run on my 32 thread workstation).
\paragraph{}
Our experiments are divided into two parts, each testing a deep learning network alongside its corresponding feed-forward network. For a fair comparison, the feed-forward test focuses explicitly on the feed-forward component of the deep learning network. This ensures that variables such as the number of layers or nodes in the feed-forward section remain consistent, minimizing potential biases and maintaining the integrity of our comparisons.
\section{Experiment 1}
\paragraph{}
Our first experiment compares using the included example from the DLIB C++ library. Specifically the deep learning test consists of
Our first experiment compares using the included example from the DLIB C++ library. Specifically the deep learning test consists of two ReLu convolutions, the first of which has six filters sized 5x5 with a 1x1 stride. The second has sixteen filters with the same size and stride configuration. Each convolution step is passed through a max-pooling stage set to a size of 2x2 with a stride of 2x2. The results are then passed into a three layer fully connected ReLu feed-forward network. The first layer has 120 neurons, second has 84 and the final output layer has 10 neurons, representing the class the network thinks the input image is. The other configuration in this experiment consists of only the three layer fully connected network.
\section{Experiment 2}
\paragraph{}
\paragraph{}
The second experiment keeps the same settings on the convolutions and pooling but changes the number of neurons in the layers of the feed forward section of the network. This is meant to demonstrate that as you restrict the number of parameters used for object detection and classification that the feature extractions provided by deep learning are highly beneficial.

11
latex/chapters/results.aux
View File

@ -1,8 +1,11 @@
\relax
\providecommand{\transparent@use}[1]{}
\providecommand\hyper@newdestlabel[2]{}
\@writefile{toc}{\contentsline {chapter}{\numberline {3}Results}{4}{chapter.3}\protected@file@percent }
\@writefile{lof}{\addvspace {10\p@ }}
\@writefile{lot}{\addvspace {10\p@ }}
\@setckpt{chapters/results}{
\setcounter{page}{3}
\setcounter{page}{5}
\setcounter{equation}{0}
\setcounter{enumi}{0}
\setcounter{enumii}{0}
@ -11,8 +14,8 @@
\setcounter{footnote}{0}
\setcounter{mpfootnote}{0}
\setcounter{part}{0}
\setcounter{chapter}{2}
\setcounter{section}{2}
\setcounter{chapter}{3}
\setcounter{section}{0}
\setcounter{subsection}{0}
\setcounter{subsubsection}{0}
\setcounter{paragraph}{0}
@ -40,5 +43,5 @@
\setcounter{section@level}{4}
\setcounter{Item}{0}
\setcounter{Hfootnote}{0}
\setcounter{bookmark@seq@number}{5}
\setcounter{bookmark@seq@number}{6}
}

1
latex/chapters/results.tex
View File

@ -1 +1,2 @@
\chapter{Results}

13
latex/report.aux
View File

@ -2,17 +2,6 @@
\providecommand{\transparent@use}[1]{}
\AC@reset@newl@bel
\providecommand\hyper@newdestlabel[2]{}
\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}
\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined
\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\newlabel\oldnewlabel
\fi}
\fi}
\global\let\hyper@last\relax
\gdef\HyperFirstAtBeginDocument#1{#1}
\providecommand\HyField@AuxAddToFields[1]{}
\providecommand\HyField@AuxAddToCoFields[2]{}
\@input{chapters/abstract.aux}
@ -21,4 +10,4 @@
\@input{chapters/results.aux}
\@input{chapters/conclusion.aux}
\gdef\svg@ink@ver@settings{{\m@ne }{inkscape}{\m@ne }}
\gdef \@abspage@last{5}
\gdef \@abspage@last{8}

953
latex/report.log
View File

File diff suppressed because it is too large Load Diff

1
latex/report.out
View File

@ -3,3 +3,4 @@
\BOOKMARK [0][-]{chapter.2}{\376\377\000E\000x\000p\000e\000r\000i\000m\000e\000n\000t\000a\000l\000\040\000S\000e\000t\000u\000p}{}% 3
\BOOKMARK [1][-]{section.2.1}{\376\377\000E\000x\000p\000e\000r\000i\000m\000e\000n\000t\000\040\0001}{chapter.2}% 4
\BOOKMARK [1][-]{section.2.2}{\376\377\000E\000x\000p\000e\000r\000i\000m\000e\000n\000t\000\040\0002}{chapter.2}% 5
\BOOKMARK [0][-]{chapter.3}{\376\377\000R\000e\000s\000u\000l\000t\000s}{}% 6

BIN
latex/report.pdf
View File

Binary file not shown.

BIN
latex/report.synctex.gz
View File

Binary file not shown.

6
latex/report.toc
View File

@ -5,7 +5,9 @@
\contentsline {paragraph}{}{1}{section*.6}%
\contentsline {chapter}{\numberline {2}Experimental Setup}{2}{chapter.2}%
\contentsline {paragraph}{}{2}{section*.7}%
\contentsline {section}{\numberline {2.1}Experiment 1}{2}{section.2.1}%
\contentsline {paragraph}{}{2}{section*.8}%
\contentsline {section}{\numberline {2.2}Experiment 2}{2}{section.2.2}%
\contentsline {section}{\numberline {2.1}Experiment 1}{2}{section.2.1}%
\contentsline {paragraph}{}{2}{section*.9}%
\contentsline {section}{\numberline {2.2}Experiment 2}{3}{section.2.2}%
\contentsline {paragraph}{}{3}{section*.10}%
\contentsline {chapter}{\numberline {3}Results}{4}{chapter.3}%