1034 lines
18 KiB
Plaintext
1034 lines
18 KiB
Plaintext
#LyX 2.3 created this file. For more info see http://www.lyx.org/
|
|
\lyxformat 544
|
|
\begin_document
|
|
\begin_header
|
|
\save_transient_properties true
|
|
\origin unavailable
|
|
\textclass article
|
|
\begin_preamble
|
|
\def\changemargin#1#2{\list{}{\rightmargin#2\leftmargin#1}\item[]}
|
|
\let\endchangemargin=\endlist
|
|
\pagenumbering{gobble}
|
|
|
|
\usepackage{pxfonts}
|
|
\usepackage{color}
|
|
|
|
\definecolor{commentgreen}{RGB}{0,94,11}
|
|
\definecolor{darkblue}{rgb}{0,0,0.75}
|
|
\definecolor{darkred}{rgb}{0.6,0,0}
|
|
\end_preamble
|
|
\use_default_options true
|
|
\begin_modules
|
|
customHeadersFooters
|
|
minimalistic
|
|
todonotes
|
|
\end_modules
|
|
\maintain_unincluded_children false
|
|
\language british
|
|
\language_package default
|
|
\inputencoding utf8
|
|
\fontencoding global
|
|
\font_roman "default" "default"
|
|
\font_sans "default" "default"
|
|
\font_typewriter "default" "default"
|
|
\font_math "auto" "auto"
|
|
\font_default_family default
|
|
\use_non_tex_fonts false
|
|
\font_sc false
|
|
\font_osf false
|
|
\font_sf_scale 100 100
|
|
\font_tt_scale 100 100
|
|
\use_microtype true
|
|
\use_dash_ligatures true
|
|
\graphics default
|
|
\default_output_format default
|
|
\output_sync 0
|
|
\bibtex_command biber
|
|
\index_command default
|
|
\paperfontsize default
|
|
\spacing onehalf
|
|
\use_hyperref true
|
|
\pdf_title "Training Neural Networks With Backpropagation"
|
|
\pdf_author "Andy Pack"
|
|
\pdf_subject "EEEM005"
|
|
\pdf_keywords "EEEM005"
|
|
\pdf_bookmarks true
|
|
\pdf_bookmarksnumbered false
|
|
\pdf_bookmarksopen false
|
|
\pdf_bookmarksopenlevel 1
|
|
\pdf_breaklinks false
|
|
\pdf_pdfborder true
|
|
\pdf_colorlinks false
|
|
\pdf_backref false
|
|
\pdf_pdfusetitle true
|
|
\papersize default
|
|
\use_geometry true
|
|
\use_package amsmath 1
|
|
\use_package amssymb 1
|
|
\use_package cancel 1
|
|
\use_package esint 1
|
|
\use_package mathdots 1
|
|
\use_package mathtools 1
|
|
\use_package mhchem 1
|
|
\use_package stackrel 1
|
|
\use_package stmaryrd 1
|
|
\use_package undertilde 1
|
|
\cite_engine biblatex
|
|
\cite_engine_type authoryear
|
|
\biblio_style plain
|
|
\biblio_options urldate=long
|
|
\biblatex_bibstyle ieee
|
|
\biblatex_citestyle ieee
|
|
\use_bibtopic false
|
|
\use_indices false
|
|
\paperorientation portrait
|
|
\suppress_date true
|
|
\justification true
|
|
\use_refstyle 1
|
|
\use_minted 0
|
|
\index Index
|
|
\shortcut idx
|
|
\color #008000
|
|
\end_index
|
|
\leftmargin 1.8cm
|
|
\topmargin 2cm
|
|
\rightmargin 1.8cm
|
|
\bottommargin 2cm
|
|
\secnumdepth 3
|
|
\tocdepth 3
|
|
\paragraph_separation skip
|
|
\defskip medskip
|
|
\is_math_indent 0
|
|
\math_numbering_side default
|
|
\quotes_style british
|
|
\dynamic_quotes 0
|
|
\papercolumns 1
|
|
\papersides 1
|
|
\paperpagestyle fancy
|
|
\listings_params "language=Python,breaklines=true,frame=tb,otherkeywords={self},emph={State},emphstyle={\ttb\color{darkred}},basicstyle={\ttfamily},commentstyle={\bfseries\color{commentgreen}\itshape},keywordstyle={\color{darkblue}},emphstyle={\color{red}},stringstyle={\color{red}}"
|
|
\bullet 1 0 9 -1
|
|
\bullet 2 0 24 -1
|
|
\tracking_changes false
|
|
\output_changes false
|
|
\html_math_output 0
|
|
\html_css_as_file 0
|
|
\html_be_strict false
|
|
\end_header
|
|
|
|
\begin_body
|
|
|
|
\begin_layout Title
|
|
|
|
\size giant
|
|
Training Neural Networks with Backpropagation
|
|
\end_layout
|
|
|
|
\begin_layout Author
|
|
Andy Pack
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset VSpace 15pheight%
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\align center
|
|
\begin_inset Graphics
|
|
filename surrey.png
|
|
lyxscale 15
|
|
width 40col%
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset VSpace vfill
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\noindent
|
|
\align center
|
|
EEEM005
|
|
\begin_inset Newline newline
|
|
\end_inset
|
|
|
|
May 2021
|
|
\size large
|
|
|
|
\begin_inset Newline newline
|
|
\end_inset
|
|
|
|
Department of Electrical and Electronic Engineering
|
|
\begin_inset Newline newline
|
|
\end_inset
|
|
|
|
Faculty of Engineering and Physical Sciences
|
|
\begin_inset Newline newline
|
|
\end_inset
|
|
|
|
University of Surrey
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Newpage newpage
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Section*
|
|
Executive Summary
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
Summary here
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Newpage newpage
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset ERT
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
|
|
|
|
\backslash
|
|
pagenumbering{roman}
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Abstract
|
|
abstract
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset CommandInset toc
|
|
LatexCommand tableofcontents
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Newpage pagebreak
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset FloatList figure
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset FloatList table
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Newpage pagebreak
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Right Footer
|
|
Andy Pack / 6420013
|
|
\end_layout
|
|
|
|
\begin_layout Left Footer
|
|
May 2021
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset ERT
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
|
|
|
|
\backslash
|
|
pagenumbering{arabic}
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
|
|
|
|
\backslash
|
|
setcounter{page}{1}
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Section
|
|
Introduction
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
Artificial neural networks have been the object of research and investigation
|
|
since the 1940s with
|
|
\noun on
|
|
McCulloch
|
|
\noun default
|
|
and
|
|
\noun on
|
|
Pitts
|
|
\noun default
|
|
' model of the artificial neuron
|
|
\begin_inset CommandInset citation
|
|
LatexCommand cite
|
|
key "McCulloch1943"
|
|
literal "false"
|
|
|
|
\end_inset
|
|
|
|
or
|
|
\emph on
|
|
Threshold Logic Unit
|
|
\emph default
|
|
.
|
|
Throughout the century, the development of the single and multi-layer perceptro
|
|
ns (SLP/MLP) alongside the backpropagation algorithm
|
|
\begin_inset CommandInset citation
|
|
LatexCommand cite
|
|
key "Rumelhart1986"
|
|
literal "false"
|
|
|
|
\end_inset
|
|
|
|
advanced the study of artificial intelligence.
|
|
Throughout the 2010s, convolutional neural networks have proved critical
|
|
in the field of computer vision and image recognition
|
|
\begin_inset CommandInset citation
|
|
LatexCommand cite
|
|
key "alexnet"
|
|
literal "false"
|
|
|
|
\end_inset
|
|
|
|
.
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
This work investigates the ability of a shallow multi-layer perceptron to
|
|
classify breast tumours as either benign or malignant.
|
|
The architecture and parameters were varied before exploring how in order
|
|
to evaluate how this affects performance.
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
Investigations were carried out in
|
|
\noun on
|
|
Python
|
|
\noun default
|
|
using the
|
|
\noun on
|
|
TensorFlow
|
|
\noun default
|
|
package to construct, train and evaluate neural networks.
|
|
The networks were trained using a supervised learning curriculum of labelled
|
|
data taken from a standard
|
|
\noun on
|
|
MatLab
|
|
\noun default
|
|
dataset
|
|
\begin_inset CommandInset citation
|
|
LatexCommand cite
|
|
key "matlab-dataset"
|
|
literal "false"
|
|
|
|
\end_inset
|
|
|
|
from the
|
|
\noun on
|
|
Deep Learning Toolbox
|
|
\noun default
|
|
.
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
Section
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "sec:exp1"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
investigates the effect of varying the number of hidden nodes on test accuracy
|
|
along with the number of epochs that the MLPs are trained for.
|
|
Section
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "sec:exp2"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
builds on the previous experiment by using reasonable parameter values
|
|
to investigate performance when using an ensemble of models to classify
|
|
in conjunction.
|
|
The effect of varying the number of nodes and epochs throughout the ensemble
|
|
was considered in order to determine whether combining multiple models
|
|
could produce a better accuracy than any individual model.
|
|
Section
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "sec:exp3"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
investigates the effect of altering how the networks learn by changing
|
|
the optimisation algorithm.
|
|
Two additional algorithms to the previously used are considered and compared
|
|
using the same test apparatus of section
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "sec:exp2"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
.
|
|
\end_layout
|
|
|
|
\begin_layout Section
|
|
Hidden Nodes & Epochs
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "sec:exp1"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
This section investigates the effect of varying the number of nodes in the
|
|
single hidden layer of a shallow multi-layer perceptron.
|
|
This is compared to the effect of training the model with different numbers
|
|
of epochs.
|
|
Throughout the experiment, stochastic gradient descent with momentum is
|
|
used as the optimiser, variations in both momentum and learning rate are
|
|
presented.
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Subsection
|
|
Results
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Float figure
|
|
wide false
|
|
sideways false
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
\noindent
|
|
\align center
|
|
\begin_inset Graphics
|
|
filename ../graphs/exp1-test1-error-rate-curves.png
|
|
lyxscale 50
|
|
width 50col%
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
\begin_inset Caption Standard
|
|
|
|
\begin_layout Plain Layout
|
|
Varied hidden node performance results over varied training lengths for
|
|
|
|
\begin_inset Formula $\eta=0.01$
|
|
\end_inset
|
|
|
|
,
|
|
\begin_inset Formula $p=0$
|
|
\end_inset
|
|
|
|
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "fig:exp1-test1"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
Figure
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "fig:exp1-test1"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
visualises the performance of hidden nodes up to 256 over training periods
|
|
up to 200 epochs in length.
|
|
In general, the error rate can be seen to decrease when the models are
|
|
trained for longer.
|
|
Increasing the number of nodes decreases the error rate and increases the
|
|
gradient with which it falls up to a limit.
|
|
64, 128 and 256 hidden nodes lie close together as the increases in performance
|
|
slow.
|
|
Between 0 and 25 epochs, the error rate throughout for any number of nodes
|
|
can descend little below 0.35.
|
|
The number of epochs to overcome this plateau is different for each number
|
|
of nodes.
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
The standard deviations for the above discussed results of figure
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "fig:exp1-test1"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
can be seen in figure
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "fig:exp1-test1-std"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
.
|
|
As the network starts training, the standard deviation decreases to a minimum
|
|
between
|
|
\begin_inset Formula $10-20$
|
|
\end_inset
|
|
|
|
epochs before increasing to a peak at 64.
|
|
As the number of hidden nodes increases, the standard deviation decreases.
|
|
The initial drop is sharper and the 64 epoch peak increases higher.
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Float figure
|
|
wide false
|
|
sideways false
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
\noindent
|
|
\align center
|
|
\begin_inset Graphics
|
|
filename /mnt/files/dev/py/shallow-training/graphs/exp1-test1-test-train-error-rate-std.png
|
|
lyxscale 50
|
|
width 60col%
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
\begin_inset Caption Standard
|
|
|
|
\begin_layout Plain Layout
|
|
Standard deviation of results from figure
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "fig:exp1-test1"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
with
|
|
\begin_inset Formula $\eta=0.01$
|
|
\end_inset
|
|
|
|
,
|
|
\begin_inset Formula $p=0$
|
|
\end_inset
|
|
|
|
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "fig:exp1-test1-std"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Float figure
|
|
wide false
|
|
sideways false
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
\noindent
|
|
\align center
|
|
\begin_inset Graphics
|
|
filename /mnt/files/dev/py/shallow-training/graphs/exp1-test2-2-error-rate-curves.png
|
|
lyxscale 50
|
|
width 50col%
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
\begin_inset Caption Standard
|
|
|
|
\begin_layout Plain Layout
|
|
Varied hidden node performance results over varied training lengths for
|
|
|
|
\begin_inset Formula $\eta=0.1$
|
|
\end_inset
|
|
|
|
,
|
|
\begin_inset Formula $p=0$
|
|
\end_inset
|
|
|
|
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "fig:exp1-test2-2"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Subsection
|
|
Discussion
|
|
\end_layout
|
|
|
|
\begin_layout Section
|
|
Ensemble Classification
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "sec:exp2"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
A horizontal ensemble of
|
|
\begin_inset Formula $m$
|
|
\end_inset
|
|
|
|
models was constructed with majority vote in order to investigate whether
|
|
this could improve performance over that of any single model.
|
|
In order to introduce variation between models of the ensemble, a range
|
|
for hidden nodes and epochs could be defined.
|
|
When selecting parameters throughout the ensemble, the models are equally
|
|
distributed throughout the ranges
|
|
\begin_inset Foot
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
For
|
|
\begin_inset Formula $m=1$
|
|
\end_inset
|
|
|
|
, the average of the range is taken
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
.
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
The statistic
|
|
\emph on
|
|
agreement
|
|
\emph default
|
|
,
|
|
\begin_inset Formula $a$
|
|
\end_inset
|
|
|
|
, is defined as the proportion of models under the meta-classifier that
|
|
correctly predict a sample's class when the ensemble correctly classifies.
|
|
It could also be considered the confidence of the meta-classifier, for
|
|
one horizontal model
|
|
\begin_inset Formula $a_{m=1}=1$
|
|
\end_inset
|
|
|
|
.
|
|
As error rates are presented, this is inverted by
|
|
\begin_inset Formula $1-a$
|
|
\end_inset
|
|
|
|
to
|
|
\emph on
|
|
disagreement
|
|
\emph default
|
|
,
|
|
\begin_inset Formula $d$
|
|
\end_inset
|
|
|
|
, the proportion of incorrect models when correctly group classifying.
|
|
\end_layout
|
|
|
|
\begin_layout Subsection
|
|
Results
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
For comparison, the average individual accuracy for both test and training
|
|
data are presented.
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Float figure
|
|
wide false
|
|
sideways false
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
\noindent
|
|
\align center
|
|
\begin_inset Graphics
|
|
filename ../graphs/exp2-test8-error-rate-curves.png
|
|
lyxscale 50
|
|
width 50col%
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
\begin_inset Caption Standard
|
|
|
|
\begin_layout Plain Layout
|
|
Ensemble classifier performance results for
|
|
\begin_inset Formula $\eta=0.03$
|
|
\end_inset
|
|
|
|
,
|
|
\begin_inset Formula $p=0.01$
|
|
\end_inset
|
|
|
|
, nodes = 1 - 400, epochs = 5 - 100
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "fig:exp2-test8"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
An experiment with a fixed epoch value throughout the ensemble is presented
|
|
in figure
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "fig:exp2-test10"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
.
|
|
Nodes between 1 and 400 were selected for the classifiers with a learning
|
|
rate,
|
|
\begin_inset Formula $\eta=0.15$
|
|
\end_inset
|
|
|
|
and momentum,
|
|
\begin_inset Formula $p=0.01$
|
|
\end_inset
|
|
|
|
.
|
|
The ensemble accuracy can be seen to be fairly constant throughout the
|
|
number of horizontal models with 3 models being the least accurate with
|
|
a higher standard deviation.
|
|
3 horizontal models also shows a significant spike in disagreement and
|
|
individual error rates which gradually decreases as the number of models
|
|
increases.
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Float figure
|
|
wide false
|
|
sideways false
|
|
status open
|
|
|
|
\begin_layout Plain Layout
|
|
\noindent
|
|
\align center
|
|
\begin_inset Graphics
|
|
filename ../graphs/exp2-test10-error-rate-curves.png
|
|
lyxscale 50
|
|
width 50col%
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
\begin_inset Caption Standard
|
|
|
|
\begin_layout Plain Layout
|
|
Ensemble classifier performance results for
|
|
\begin_inset Formula $\eta=0.15$
|
|
\end_inset
|
|
|
|
,
|
|
\begin_inset Formula $p=0.01$
|
|
\end_inset
|
|
|
|
, nodes =
|
|
\begin_inset Formula $1-400$
|
|
\end_inset
|
|
|
|
, epochs = 20
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "fig:exp2-test10"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Plain Layout
|
|
|
|
\end_layout
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Subsection
|
|
Discussion
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
From the data of figure
|
|
\begin_inset CommandInset ref
|
|
LatexCommand ref
|
|
reference "fig:exp2-test10"
|
|
plural "false"
|
|
caps "false"
|
|
noprefix "false"
|
|
|
|
\end_inset
|
|
|
|
, 3 horizontal models was shown to be the worst performing configuration
|
|
with lower ensemble accuracy and higher disagreement.
|
|
This is likely due to larger proportion that a single model constitutes.
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Section
|
|
Optimiser Comparisons
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "sec:exp3"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
Throughout the previous experiments the stochastic gradient descent optimiser
|
|
was used to change the networks weights but there are many different optimisati
|
|
on algorithms.
|
|
This section will present investigations into two other optimisation algorithms
|
|
and discuss the differences between them using the horizontal ensemble
|
|
classification of the previous section.
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
Prior to these investigations, however, stochastic gradient descent and
|
|
the two other subject algorithms will be described.
|
|
\end_layout
|
|
|
|
\begin_layout Subsection
|
|
Optimisers
|
|
\end_layout
|
|
|
|
\begin_layout Subsubsection
|
|
Stochastic Gradient Descent
|
|
\end_layout
|
|
|
|
\begin_layout Subsubsection
|
|
RMSprop
|
|
\end_layout
|
|
|
|
\begin_layout Subsubsection
|
|
Adam
|
|
\end_layout
|
|
|
|
\begin_layout Subsection
|
|
Results
|
|
\end_layout
|
|
|
|
\begin_layout Subsection
|
|
Discussion
|
|
\end_layout
|
|
|
|
\begin_layout Section
|
|
Conclusions
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset Newpage newpage
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset CommandInset label
|
|
LatexCommand label
|
|
name "sec:bibliography"
|
|
|
|
\end_inset
|
|
|
|
|
|
\begin_inset CommandInset bibtex
|
|
LatexCommand bibtex
|
|
btprint "btPrintCited"
|
|
bibfiles "references"
|
|
options "bibtotoc"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\begin_layout Section
|
|
\start_of_appendix
|
|
Source Code
|
|
\end_layout
|
|
|
|
\begin_layout Standard
|
|
\begin_inset CommandInset include
|
|
LatexCommand lstinputlisting
|
|
filename "../nncw.py"
|
|
lstparams "caption={Formatted Jupyter notebook containing experiment code},label={notebook-code}"
|
|
|
|
\end_inset
|
|
|
|
|
|
\end_layout
|
|
|
|
\end_body
|
|
\end_document
|