deepsad flow diagram

thesis/Main.tex

@@ -518,7 +518,7 @@ The pre-training results are used in two more key ways. First, the encoder weigh
 
 In the main training step, DeepSAD's network is trained using SGD backpropagation. The unlabeled training data is used with the goal to minimize an data-encompassing hypersphere. Since one of the pre-conditions of training was the significant prevelance of normal data over anomalies in the training set, normal samples collectively cluster more tightly around the centroid, while the rarer anomalous samples do not contribute as significantly to the optimization, resulting in them staying further from the hypersphere center. The labeled data includes binary class labels signifying their status as either normal or anomalous samples. Labeled anomalies are pushed away from the center by defining their optimization target as maximizing the distance between them and $\mathbf{c}$. Labeled normal samples are treated similar to unlabeled samples with the difference that DeepSAD includes a hyperparameter capable of controling the proportion with which labeled and unlabeled data contribute to the overall optimization. The resulting network has learned to map normal data samples closer to $\mathbf{c}$ in the latent space and anomalies further away.
 
-\todo[inline]{maybe pseudocode algorithm block?}
+\fig{deepsad_procedure}{diagrams/deepsad_procedure}{WIP: Depiction of DeepSAD's training procedure, including data flows and tweakable hyperparameters.}
 
 \threadtodo
 {how to use the trained network?}

thesis/bib/bibliography.bib

@@ -454,6 +454,20 @@
   year = {2023},
   month = oct,
   pages = {1–7},
+},
+@article{lidar_denoising_dust,
+  title = {Dust De-Filtering in LiDAR Applications With Conventional and CNN
+           Filtering Methods},
+  volume = {12},
+  ISSN = {2169-3536},
+  url = {http://dx.doi.org/10.1109/ACCESS.2024.3362804},
+  DOI = {10.1109/access.2024.3362804},
+  journal = {IEEE Access},
+  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
+  author = {Parsons, Tyler and Seo, Jaho and Kim, Byeongjin and Lee, Hanmin and
+            Kim, Ji-Chul and Cha, Moohyun},
+  year = {2024},
+  pages = {22032–22042},
 }
 
 

thesis/diagrams/deepsad_procedure.tex

@@ -0,0 +1,143 @@
+\documentclass[tikz,border=10pt]{standalone}
+\usepackage{tikz}
+\usetikzlibrary{positioning, shapes.geometric, fit, arrows, arrows.meta, backgrounds}
+
+% Define box styles
+\tikzset{
+  databox/.style={rectangle, align=center, draw=black, fill=blue!50, thick, rounded corners},%, inner sep=4},
+  procbox/.style={rectangle, align=center, draw=black, fill=orange!30, thick, rounded corners},
+  hyperbox/.style={rectangle, align=center, draw=black, fill=green!30, thick, rounded corners},
+  stepsbox/.style={rectangle, align=left, draw=black,fill=white, rounded corners, minimum width=6cm, minimum height=1.5cm, font=\small},
+  outputbox/.style={rectangle, align=center, draw=red!80, fill=red!20, rounded corners, minimum width=6cm, minimum height=1.5cm, font=\small},
+  hlabelbox/.style={rectangle, align=center, draw=black,fill=white, rounded corners, minimum width=6cm, minimum height=1.5cm, font=\small},
+  vlabelbox/.style={rectangle, align=center, draw=black,fill=white, rounded corners, minimum width=3cm, minimum height=1.8cm, font=\small},
+  arrow/.style={-{Latex[length=3mm]}},
+  arrowlabel/.style={fill=white,inner sep=2pt,midway}
+}
+
+\newcommand{\boxtitle}[1]{\textbf{#1}\\[.4em]}
+
+\pgfdeclarelayer{background}
+\pgfdeclarelayer{foreground}
+\pgfsetlayers{background,main,foreground}
+
+\begin{document}
+\begin{tikzpicture}[node distance=1cm and 2cm]
+
+	\node (data) {Data};
+	\node[right=7 of data] (process) {Procedure};
+	\node[right=7 of process] (hyper) {Hyperparameters};
+
+	\begin{pgfonlayer}{foreground}
+		\node[hlabelbox, below=of data] (unlabeled) {\boxtitle{Unlabeled Data} More normal than \\ anomalous samples required};
+		\node[hlabelbox, below=.1 of unlabeled] (labeled) {\boxtitle{Labeled Data} No requirement regarding ratio \\ +1 = normal, -1 = anomalous};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[databox, fit=(unlabeled) (labeled), label={[label distance = 1, name=traindatalabel]above:{\textbf{Training Data}}}] (traindata) {};
+	\end{pgfonlayer}
+
+	%\draw[arrow] (latent.east) -- node{} (autoenc.west);
+
+	\begin{pgfonlayer}{foreground}
+		\node[stepsbox, below=of process] (pretrainproc) {Train Autoencoder for $E_A$ Epochs \\ with $L_A$ Learning Rate \\ No Labels Used};
+		\node[outputbox, below=.1 of pretrainproc] (pretrainout) {\boxtitle{Outputs} Encoder Network \\ $\mathbf{w}$: Network Weights};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[procbox, fit=(pretrainproc) (pretrainout), label={[label distance = 1, name=pretrainlab]above:{\textbf{Pre-Training of Autoencoder}}}] (pretrain) {};
+	\end{pgfonlayer}
+
+	\begin{pgfonlayer}{foreground}
+		\node[hlabelbox, below=of hyper] (autoencarch) {\boxtitle{Autoencoder Architecture} Choose based on data type \\ Latent Space Size};
+		\node[hlabelbox, below=.1 of autoencarch] (pretrainhyper) {\boxtitle{Hyperparameters} $E_A$: Number of Epochs  \\ $L_A$: Learning Rate};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[hyperbox, fit=(autoencarch) (pretrainhyper), label={[label distance = 1, name=autoenclabel]above:{\textbf{Pre-Training Hyperparameters}}}] (pretrainhyp) {};
+	\end{pgfonlayer}
+
+	\draw[arrow] (pretrainhyp.west) -- (pretrain.east);
+
+	%\draw[arrow] (node cs:name=traindata,angle=10) -- node[arrowlabel]{data type} (node cs:name=autoenc,angle=177);
+
+	%	\draw[arrow] (node cs:name=autoenc,angle=196) |- (node cs:name=pretrain,angle=5);
+
+	\begin{pgfonlayer}{foreground}
+		\node[stepsbox, below=1.4 of pretrain] (calccproc) {1. Init Encoder with $\mathbf{w}$ \\ 2. Forward Pass on all data \\ 3. $\mathbf{c}$ = Mean Latent Representation};
+		\node[outputbox, below=.1 of calccproc] (calccout) {\boxtitle{Outputs} $\mathbf{c}$: Hypersphere Center};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[procbox, fit=(calccproc) (calccout), label={[label distance = 1, name=calcclab]above:{\textbf{Calculate Hypersphere Center}}}] (calcc) {};
+	\end{pgfonlayer}
+
+	\draw[arrow] (pretrain.south) -- (calcclab.north);
+	\draw[arrow] (traindata.east) -- (pretrain.west);
+	\draw[arrow] (traindata.south) |- (calcc.west);
+
+	%\draw[arrow] (node cs:name=traindata,angle=45) |- node[arrowlabel]{all training data, labels removed} (node cs:name=pretrain,angle=160);
+	%\draw[arrow] (node cs:name=traindata,angle=-45) |- node[arrowlabel]{all training data, labels removed} (node cs:name=calcc,angle=200);
+
+	\begin{pgfonlayer}{foreground}
+		\node[stepsbox, below=1.4 of calcc] (maintrainproc) {Train Network for $E_M$ Epochs \\ with $L_M$ Learning Rate \\ Considers Labels};
+		\node[outputbox, below=.1 of maintrainproc] (maintrainout) {\boxtitle{Outputs} Encoder Network \\ $\mathbf{w}$: Network Weights  \\ $\mathbf{c}$: Hypersphere Center};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[procbox, fit=(maintrainproc) (maintrainout), label={[label distance = 1, name=maintrainlab]above:{\textbf{Main Training}}}] (maintrain) {};
+	\end{pgfonlayer}
+
+	\begin{pgfonlayer}{foreground}
+		\node[hlabelbox, below=11.25 of hyper] (maintrainhyper) {$E_M$: Number of Epochs  \\ $L_M$: Learning Rate  \\ $\eta$: Strength Labeled/Unlabeled};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[hyperbox, fit=(maintrainhyper), label={[label distance = 1, name=autoenclabel]above:{\textbf{Main-Training Hyperparameters}}}] (maintrainhyp) {};
+	\end{pgfonlayer}
+
+	%\draw[arrow] (pretrainoutput.south) -- (node cs:name=maintrain,angle=22);
+	\draw[arrow] (calcc.south) -- (maintrainlab.north);
+	\draw[arrow] (traindata.south) |- (maintrain.west);
+	%\draw[arrow] (node cs:name=traindata,angle=-135) |- node[arrowlabel]{all training data, including labels} (maintrain.west);
+	\draw[arrow] (maintrainhyp.west) -- (maintrain.east);
+
+
+	\begin{pgfonlayer}{foreground}
+		\node[stepsbox, below=1.4 of maintrain] (inferenceproc) {Forward Pass through Network = $\mathbf{p}$ \\ Calculate Geometric Distance $\mathbf{p} \rightarrow \mathbf{c}$ \\ Anomaly Score = Geometric Distance};
+		\node[outputbox, below=.1 of inferenceproc] (inferenceout) {\boxtitle{Outputs} Anomaly Score (Analog Value) \\ Higher for Anomalies};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[procbox, fit=(inferenceproc) (inferenceout), label={[label distance = 1, name=inferencelab]above:{\textbf{Inference}}}] (inference) {};
+	\end{pgfonlayer}
+
+	\begin{pgfonlayer}{foreground}
+		\node[hlabelbox, below=11.8 of traindata] (newdatasample) {\boxtitle{New Data Sample} Same data type as training data};
+	\end{pgfonlayer}
+	\begin{pgfonlayer}{background}
+		\node[databox, fit=(newdatasample),  label={[label distance = 1] above:{\textbf{Unseen Data}}}] (newdata) {};
+	\end{pgfonlayer}
+
+	\draw[arrow] (maintrain.south) -- (inferencelab.north);
+	\draw[arrow] (newdata.east) -- (inference.west);
+
+\end{tikzpicture}
+\end{document}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+