\setcounter{numTAs}{0}
\setcounter{totalSections}{1}
\def\secNum{{"001",""}}
\def\tenSchFileName{{"",""}}
\def\classTime{{"MW from 03:00 pm to 04:15 pm",""}}
\def\classRm{{"Tolentine 308",""}}
\def\classLive{{"",""}}
\def\classInstructor{{"Xun Jiao",""}}
\def\classInstrContact{{"",""}}
\def\classInstrOffHrs{{"Monday from 1pm - 3pm or by Appointment",""}}
\def\classInstrLive{{"",""}}
\def\TA{{{""},{""}}}
\def\TAEmail{{{""},{""}}}
\def\TAOffHrs{{{""},{""}}}
\def\TARoom{{{""},{""}}}
\newcommand\semester{Spring 2022}
\newcommand\rsemester{202230}
\newcommand\courseNum{ECE 5400}
\newcommand\courseName{Applied Machine Learning}
\newcommand\courseCoordinator{Xun Jiao}
\newcommand\credits{3}
\newcommand\contactHrs{3}
\newcommand\lecture{1}
\newcommand\lab{0}
\newcommand\undergradCourse{1}
\newcommand\isFreshmanCourse{0}
\newcommand\isCustomElecPolicy{0}
\newcommand\isClassLive{0}
\newcommand\isLabLive{0}
\newcommand\meetingMiscExists{0}
\newcommand\isClassInstrLive{0}
\newcommand\isLabInstrLive{0}
\newcommand\instrMiscExists{0}
\newcommand\hasTARoom{0}
\newcommand\meetingDesc{Two 75-minute lectures}
\newcommand\meetingMisc{Special notes on meeting info go here, if specified}
\newcommand\instructorMisc{Special notes on instructor(s), TA(s) go here, if specified}
\newcommand\textBookExists{0}
\newcommand\textBookReqd{0}
\newcommand\textBookMiscExists{1}
\newcommand\referencesExist{0}
\newcommand\txtBkAuthExists{0}
\newcommand\txtBkPublExists{0}
\newcommand\txtBkYrExists{0}
\newcommand\txtBkISBNExists{0}
\newcommand\textBookTitle{}
\newcommand\textBookAuth{}
\newcommand\textBookPub{}
\newcommand\textBookYr{}
\newcommand\textBookISBN{}
\newcommand\supplMaterials{}
\newcommand\refPapers{References go here, if specified}
\newcommand\textBookMisc{Special notes on textbook(s) go here, if specified}
\newcommand\catalogDesc{In this course, we will study how to develop and apply machine learning methods to different application domains as well as efficient processing of machine learning methods. We will study state-of-the-art machine learning frameworks such as Facebook’s PyTorch or Google’s TensorFlow. We will study the basic knowledge of various machine learning models, such as logistic regression, support vector machine, and neural networks. We will also study optimization techniques such as compression and pruning to enable efficient processing of neural networks. In this course, we will thoroughly examine the emerging trends in industry to understand the underlying research challenges and opportunities. We will implement the machine learning methods and apply on real-world datasets. We will optimize the existing neural networks model using covered techniques and evaluate its effectiveness.}
\newcommand\preReqs{Python, Linear Algebra}
\newcommand\coReqs{None}
\newcommand\coreRequirement{Technical Elective}
\newcommand\courseExpectation{Learn how to develop machine learning models; learn the theoretical aspects of various machine learning algorithms.}
\newcommand\ABETOutOne{1}
\newcommand\ABETOutTwo{0}
\newcommand\ABETOutThree{0}
\newcommand\ABETOutFour{0}
\newcommand\ABETOutFive{0}
\newcommand\ABETOutSix{0}
\newcommand\ABETOutSeven{0}
\newcommand\covTopics{\item Logistic Regression
\item Support Vector Machine
\item Decision Tree
\item Applications on real-world datasets
\item Neural Networks}
\newcommand\isScheduleExternal{0}
\newcommand\isScheduleCommon{1}
\newcommand\scheduleRows{17}
\newcommand\scheduleCols{2}
\newcommand\scheduleHeight{1}
\newcommand\schedule{\begin{table}[h!] \centering 
\caption*{Tentative Schedule for \textbf{All Sections}} \vspace{0.05in}
{\renewcommand{\arraystretch}{1.5} \small
\begin{tabularx}{\linewidth}{c|l}
\toprule
\large \textbf{Week or Date} & \large \textbf{Topics or whatever}\\
\midrule \midrule
1 & Introduction to ML\\
2 & ML Tasks\\
3 & ML Evaluation\\
4 & Linear Regression\\
5 & Logistic Regression\\
6 & Decision Tree\\
7 & Random Forest\\
8 & Spring Break\\
9 & Multi-Layer Perceptron\\
10 & Convolutional Neural Networks\\
11 & Convolutional Neural Networks\\
12 & Recurrent Neural Networks\\
13 & Reinforcement Learning\\
14 & Easter Break\\
15 & Deep Learning\\
16 & Final Project\\
\bottomrule \end{tabularx} } \end{table}}
\newcommand\gradingPolicy{Assignments - 40\% \\ 
Midterm - 30\% \\
Final - 30\% \\
\\
Letter grade scale: A(94–100), A–(90–93), B+(87–89), B(83–86), B–(80–82), C+(77–79), C(73–76), C–(70–72),
D+(67–69), D(63–66), D–(60–62), F(<60) \\ 
Late submissions will be assessed a 10% penalty per day.}
\newcommand\HWandLabPolicy{}
\newcommand\AttendancePolicy{\textcolor{red}{State here if attendance is mandatory or not for your class. Provide a description of what it means to be present (e.g. seated and ready to go, or just in the room; be explicit).}}
\newcommand\ElectronicsPolicy{\textcolor{red}{Since you opted for a customize electronics policy, you should edit this part. Your policy should address your general stance on recording of class sessions and the circumstances under which recording will be allowed or prohibited. If you generally prohibit recording, yet allow recording of certain classes for some reason, then you should notify all students that those classes will be recorded. If recording is permitted as an ADA accommodation for a student, you obviously should not identify that student(s).}}