began writing report, added nbconvert script

This commit is contained in:
andy 2021-04-06 21:15:26 +01:00
parent a28f36249f
commit 68760bde6b
5 changed files with 264 additions and 4 deletions

1
.gitignore vendored
View File

@ -5,6 +5,7 @@ __pycache__/
*.pdf *.pdf
*~* *~*
*#*
*.bak *.bak
*.sav *.sav

Binary file not shown.

Before

Width:  |  Height:  |  Size: 471 KiB

After

Width:  |  Height:  |  Size: 401 KiB

3
nbgen Executable file
View File

@ -0,0 +1,3 @@
#!/usr/bin/env bash
python -m jupyter nbconvert --to script nncw.ipynb

View File

@ -1,3 +1,54 @@
% Encoding: UTF-8 @comment{x-kbibtex-encoding=utf-8}
@comment{jabref-meta: databaseType:bibtex;}
@article{McCulloch1943,
abstract = {Because of the “all-or-none” character of nervous activity, neural events and the relations among them can be treated by means of propositional logic. It is found that the behavior of every net can be described in these terms, with the addition of more complicated logical means for nets containing circles; and that for any logical expression satisfying certain conditions, one can find a net behaving in the fashion it describes. It is shown that many particular choices among possible neurophysiological assumptions are equivalent, in the sense that for every net behaving under one assumption, there exists another net which behaves under the other and gives the same results, although perhaps not in the same time. Various applications of the calculus are discussed.},
author = {McCulloch, Warren S. and Pitts, Walter},
doi = {10.1007/BF02478259},
issn = {1522-9602},
journal = {The bulletin of mathematical biophysics},
number = {4},
pages = {115133},
risfield_0_da = {1943/12/01},
title = {A logical calculus of the ideas immanent in nervous activity},
url = {https://link.springer.com/article/10.1007/BF02478259},
urldate = {2021-04-06},
volume = {5},
year = {1943}
}
@article{Rumelhart1986,
abstract = {We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal hidden units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.},
author = {Rumelhart, David E. and Hinton, Geoffrey E. and Williams, Ronald J.},
doi = {10.1038/323533a0},
issn = {1476-4687},
journal = {Nature},
number = {6088},
pages = {533536},
risfield_0_da = {1986/10/01},
title = {Learning representations by back-propagating errors},
url = {https://www.nature.com/articles/323533a0},
urldate = {2021-04-06},
volume = {323},
year = {1986}
}
@misc{matlab-dataset,
author = {MathWorks},
title = {Sample Data Sets for Shallow Neural Networks},
url = {https://es.mathworks.com/help/deeplearning/gs/sample-data-sets-for-shallow-neural-networks.html},
urldate = {2021-04-06}
}
@article{alexnet,
author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
journaltitle = {Advances in neural information processing systems},
pages = {10971105},
title = {ImageNet Classification with Deep Convolutional Networks},
url = {https://kr.nvidia.com/content/tesla/pdf/machine-learning/imagenet-classification-with-deep-convolutional-nn.pdf},
urldate = {2021-04-05},
volume = {25},
year = {2012}
}
@Comment{jabref-meta: databaseType:bibtex;}

View File

@ -24,7 +24,7 @@ minimalistic
todonotes todonotes
\end_modules \end_modules
\maintain_unincluded_children false \maintain_unincluded_children false
\language english \language british
\language_package default \language_package default
\inputencoding utf8 \inputencoding utf8
\fontencoding global \fontencoding global
@ -100,7 +100,7 @@ todonotes
\defskip medskip \defskip medskip
\is_math_indent 0 \is_math_indent 0
\math_numbering_side default \math_numbering_side default
\quotes_style english \quotes_style british
\dynamic_quotes 0 \dynamic_quotes 0
\papercolumns 1 \papercolumns 1
\papersides 1 \papersides 1
@ -293,16 +293,221 @@ setcounter{page}{1}
Introduction Introduction
\end_layout \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 those individually.
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 \begin_layout Section
Hidden Nodes & Epochs (Exp 1) Hidden Nodes & Epochs (Exp 1)
\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 hidden nodes
in a single hidden layer of a multi-layer perceptron.
This is compared to the effect of varying
\end_layout
\begin_layout Subsection
Results
\end_layout
\begin_layout Subsection
Discussion
\end_layout \end_layout
\begin_layout Section \begin_layout Section
Ensemble Classification (Exp 2) Ensemble Classification (Exp 2)
\begin_inset CommandInset label
LatexCommand label
name "sec:exp2"
\end_inset
\end_layout
\begin_layout Subsection
Results
\end_layout
\begin_layout Subsection
Discussion
\end_layout \end_layout
\begin_layout Section \begin_layout Section
Optimiser Comparisons (Exp 3) Optimiser Comparisons (Exp 3)
\begin_inset CommandInset label
LatexCommand label
name "sec:exp3"
\end_inset
\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 \end_layout
\begin_layout Section \begin_layout Section