From 419d06e6b9abba61167b37137332446722b83f66 Mon Sep 17 00:00:00 2001
From: lukas-heiligenbrunner <lukas.heiligenbrunner@gmail.com>
Date: Wed, 22 May 2024 16:46:22 +0200
Subject: [PATCH] fix typos

---
 src/introduction.tex       | 4 ++--
 src/materialandmethods.tex | 2 +-
 src/sources.bib            | 8 ++++++++
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/src/introduction.tex b/src/introduction.tex
index b7ba024..b2bcbcd 100644
--- a/src/introduction.tex
+++ b/src/introduction.tex
@@ -5,7 +5,7 @@ With too less training data the model will not generalize well and not fit a rea
 Labeling datasets is commonly seen as an expensive task and wants to be avoided as much as possible.\cite{generalAI}
 That's why there is a machine-learning field called active learning.
 The general approach is to train a model that predicts within every iteration a ranking metric or Pseudo-Labels which then can be used to rank the importance of samples to be labeled by an oracle.
-These labeled are then used to train the model.\cite{activelearning}
+These labeled samples are then used to train the model.\cite{activelearning}
 
 The goal of this practical work is to test active learning within a simple classification task and evaluate its performance.
 \subsection{Research Questions}\label{subsec:research-questions}
@@ -25,5 +25,5 @@ In section~\ref{sec:material-and-methods} we talk about general methods and mate
 First the problem is modeled mathematically in~\ref{subsubsec:mathematicalmodeling} and then implemented and benchmarked in a Jupyter notebook~\ref{subsubsec:jupyternb}.
 Section~\ref{sec:implementation} gives deeper insights to the implementation for the interested reader with some code snippets.
 The experimental results~\ref{sec:experimental-results} are well-presented with clear figures illustrating the performance of active learning across different sample sizes and batch sizes.
-The conclusion~\ref{subsec:conclusion} provides a overview of the findings, highlighting the benefits of active learning.
+The conclusion~\ref{subsec:conclusion} provides an overview of the findings, highlighting the benefits of active learning.
 Additionally the outlook section~\ref{subsec:outlook} suggests avenues for future research which are not covered in this work.
\ No newline at end of file
diff --git a/src/materialandmethods.tex b/src/materialandmethods.tex
index 20f681f..9ea682a 100644
--- a/src/materialandmethods.tex
+++ b/src/materialandmethods.tex
@@ -143,7 +143,7 @@ Finally, after some convolution layers the feature map is flattened and passed t
 \begin{figure}
     \centering
     \includegraphics[width=\linewidth]{../rsc/cnn_architecture}
-    \caption{Architecture convolutional neural network. Image by \href{https://cointelegraph.com/explained/what-are-convolutional-neural-networks}{SKY ENGINE AI}}
+    \caption{Architecture convolutional neural network. \cite{cnnarchitectureimg}}
     \label{fig:cnn-architecture}
 \end{figure}
 
diff --git a/src/sources.bib b/src/sources.bib
index c8c9d30..bc618ea 100644
--- a/src/sources.bib
+++ b/src/sources.bib
@@ -134,4 +134,12 @@ doi = {10.1007/978-0-387-85820-3_23}
     eprint={1512.03385},
     archivePrefix={arXiv},
     primaryClass={cs.CV}
+}
+
+@misc{cnnarchitectureimg,
+    author = {},
+    title = {{What are convolutional neural networks?}},
+    howpublished = "\url{https://cointelegraph.com/explained/what-are-convolutional-neural-networks}",
+    year = {2024},
+    note = "[Online; accessed 12-April-2024]"
 }
\ No newline at end of file