SYLLABUS

Introduction to Machine Learning Applications

43672 MGMT-6560-01 (3 credits) /43510 MGMT-4966-01 (4 Credits)
Spring 2021 Monday & Thursday 12:20 PM – 2:10 PM
Room Location: SAGE 3510 and Webex (https://rensselaer.webex.com/meet/manikl)
Websites: https://spring2021introtoml.github.io/ and Blackboard
Prerequisites or Other Requirements: None.

Students may not receive credit for both the 4000 level and 6000 level versions of this
course.

INSTRUCTOR
Instructor Name: Lydia Manikonda Office Location: Pitts 1212
Tel. No.: 518-276-2768 Email Address: [email protected]
Office Hours: Tuesday 12 PM to 2 PM via webex
(https://rensselaer.webex.com/rensselaer/j.php?MTID=m9947135e55d6894615a6699b2e669e46)

Grader
TA Name(s): Yuanyuan Liu TA Office Location: 2nd Floor
Pittsburgh
TA(s) Email Address: [email protected]
TA Office Hours: Friday 11 am – 1 pm (https://rensselaer.webex.com/meet/liuy55)

COURSE DESCRIPTION:
The widespread proliferation of IT-influenced economic activity leaves behind a rich trail of
micro-level data, enabling organizations to use analytics and experimentation in both
strategy and operations. This course provides a hands-on introduction to the concepts,
methods and processes for machine learning from data, the foundation of artificial
intelligence. We will learn how to manipulate data and apply machine learning models to
business contexts. Please find the attached document about the guidelines to
students on how the classes will be continued virtually.

COURSE GOALS/OBJECTIVES
Syllabus 1 of 7 4.15.2021
The goal of this course will be to provide the technical foundation to enable students to
become data scientists.

STUDENT LEARNING OUTCOMES

For MGMT6560 through this course you are expected to:
(1) Demonstrate an understanding of analytics-based problem solving and analytics
thinking in the context of machine learning models, deep learning, and big data.
(2) Be able to extract, match, transform, and clean data from a variety of sources.
(3) Develop machine learning predictions for business applications.
(4) Apply ethical frameworks to the creation of models.
(5) Translate research on state of the art deep learning to business applications.

For MGMT4966, through this course you are expected to:

(1) Demonstrate an understanding of analytics-based problem solving and analytics
thinking in the context of machine learning models, deep learning, and big data.
(2) Be able to extract, match, transform, and clean data from a variety of sources.
(3) Develop machine learning predictions for business applications.

COURSE REFERENCE MATERIALS

There is no text book that adequately covers all of the conceptual and technical issues we
will be covering in this course. However, there are a number of different books that we will
assign readings from. These books are available online with links from the course website
specifically the below mentioned textbook:

Author. Aurélien Géron

Title. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts,
Tools, and Techniques to Build Intelligent Systems
ISBN. • ISBN-10: 1492032646 • ISBN-13: 978-1492032649
Edition. 2nd Edition
Website: https://github.com/ageron/handson-ml2

COURSE ASSESSMENT MEASURES

Assignments
You will have assignments associated with many classes. Be sure to check the course
website and submit assignments via blackboard. Preparing the case questions in advance
is expected to help you participate and contribute to class discussion.

Syllabus 2 of 7 4.15.2021
You will have 3 days of “late” time for sickness/deadline conflicts. You must send a Webex
teams message or email to the instructor prior to the due date. After that there will be a
reduction of 20% per day for each late day.

Quizzes
There will be several surprise quizzes through the semester to incentivize you to review
the readings prior to class and arrive on time. The door will be locked at the start of class
on a quiz day and you will receive a 0 if you arrive late.

Project
There will be an individual data assignment to be completed as part of the class. The
overall goal is to undergo all stages of the data understanding, data munging,
visualization, modelling, and further development of understanding.

Research Translation Exercise

The student should read a recent research paper from a leading machine learning
conference (ICLR/NIPS/AAAI etc.) and explain the problem being solved, why the problem
is important, the findings, and the business implications in non-technical language suitable
for managers.

GRADING CRITERIA

All grading is out of 100%. Grade breakdown and feedback will be given through the
course learning management system.

MGMT6560 (3 Credits):

Component Weight
Assignments and Quizzes 15%
Research Translation Exercise 5%
Project* 25%
Midterm 25%
Final Exam 30%

MGMT4966 (4 Credits):

Component Weight
Assignments and Quizzes 20%
Project* 25%
Midterm 25%
Syllabus 3 of 7 4.15.2021
 Final Exam 30%

Students in MGMT6560 level cannot receive “D/D+/D-” grades.

Students should check LMS for grades on assignments.

ATTENDANCE POLICY
PLEASE DO NOT BE LATE TO CLASS. A maximum of 2 unexcused absences are allowed.
Further absences will result in a 10% reduction of Homework/Lab grades.

Labs are designed to be worked on during class time in a collaborative environment in which you
each help one another. We have very different levels of technical expertise in the class, and it is
important to work together on the labs to help one another in a classroom environment. While you
may be able to complete the work at home by yourself, in doing so you will be robbing your
classmates of your expertise. I will consider helping behaviours during the class as part of the
participation component of the class.

Therefore, the imperative clearly stated: each participant attends class fully prepared, willing and
able to offer constructive criticism, provide goal-oriented analytic and synthetic insights, and
encourage investigative dialectic. You earn your grade on participation through consistent, daily
contribution. Merely "COMING TO CLASS” is not sufficient, but is necessary.

Simply put: Do not miss class hours or group meetings! Understandably, there are circumstances
(e.g., job interviews, family matters, extracurricular activity, etc.) that may cause you to miss class;
nevertheless, excessive absences will reduce your class participation grade. Notify the instructor
and group IN ADVANCE of any planned absences (especially students who participate in
extracurricular activities as representatives of RPI.)

OTHER COURSE POLICIES

After the add deadline, assignments up to 24 hours late will have their grade reduced by
25%; assignments up to one week late will have their grade reduced by 50%. After one
week, late assignments will receive no credit. Please turn in your assignment early if there
is any uncertainty about your ability to turn it in on time.

ACADEMIC INTEGRITY

Student-teacher relationships are built on trust. For example, students must trust that
teachers have made appropriate decisions about the structure and content of the courses
they teach, and teachers must trust that the assignments that students turn in are their
own. Acts that violate this trust undermine the educational process. The Rensselaer
Handbook of Student Rights and Responsibilities and the Graduate Student Supplement

Syllabus 4 of 7 4.15.2021
(For Graduate courses) define various forms of Academic Dishonesty and you should
make yourself familiar with these. In this class, all assignments that are turned in for a
grade must represent the student’s own work. In cases where help was received, or
teamwork was allowed, a notation on the assignment should indicate your collaboration.
Submission of any assignment that is in violation of this policy will result in a grade of
zero will be given on the first assignment where a violation is detected, and the
infraction will be reported to the Associate Dean for Academic Affairs. If there is a
subsequent infraction the student will receive a grade of F for the course.

If you have any question concerning this policy before submitting an assignment, please
ask for clarification.

ACADEMIC ACCOMMODATIONS
Rensselaer Polytechnic Institute strives to make all learning experiences as accessible as
possible. If you anticipate or experience academic barriers based on a disability, please let
me know immediately so that we can discuss your options.
To establish reasonable accommodations, please register with The Office of Disability
Services for Students (mailto:[email protected]; 518-276-8197; 4226 Academy Hall). After
registration, make arrangements with me as soon as possible to discuss your
accommodations so that they may be implemented in a timely fashion.”

COURSE CALENDAR
This is a tentative schedule and subject to change depending upon the progress of the
class. Always check course website for the latest updates.

Syllabus 5 of 7 4.15.2021
Wk Day Date Topic Deadlines
1 M 1/25 Course Overview & Introduction to the Data Science Lifecycle
1 Th 1/28 Python Basics; HW1
2 M 2/1 Python conditionals, loops, functions, aggregating.
2 Th 2/4 Python conditionals, loops, functions, aggregating (continued); HW2 HW1 due
3 M 2/8 Python visualization, data manipulation , and feature creation.
3 Th 2/11 Python visualization, data manipulation , and feature creation HW2 due
4 M 2/15 President’s day holiday – NO CLASS
4 Th 2/18 Overview of Modeling; HW3
5 M 2/22 Overview of Modeling
5 Th 2/25 Modeling evaluation; HW4 HW3 due
6 M 3/1 Features and Dimensionality Reduction
6 Th 3/4 Regression and Decision Trees; HW5 HW4 due
7 M 3/8 Regression and Decision Trees
7 Th 3/11 Unsupervised Models; HW6 HW5 due
8 M 3/15 Unsupervised Models
8 Th 3/18 Text and NLP HW6 due
9 M 3/22 Revision; Project description;
9 Th 3/25 Midterm Exam (in-class); EXAM
10 M 3/29 Text and NLP
10 Th 4/1 Time Series Analysis; Advanced supervised models HW7
11 M 4/5 Advanced supervised models
11 Th 4/8 Image Data and Deep Learning (In-class RLT 6000 level); HW8 HW7 due
12 M 4/12 Deep Learning; Guest speaker: Prof. Anjana Susarla
W 4/14 Homework submission day HW8 due
12 Th 4/15 Lally wellness day holiday – NO CLASS
13 M 4/19 Deep Learning – Intro to Neural Nets; CNNs
13 Th 4/22 Final Presentations – group 1
14 M 4/26 Final Presentations – group 2
14 Th 4/29 Final Presentations – group 3 and report due Project report due
15 M 5/3 Revision of concepts
5/10 Final Exam Part-A (in-class) 8 am to 11 am ET via Webex Part-A Final exam
5/11 Final Exam Part-B (Take-home) To be submitted by 10:59 am ET Part-B Final exam

Syllabus 6 of 7 4.15.2021
COVID-19 Syllabus Guidelines – Lally School of Management

Students taking Lally School of Management classes are required to abide by the
COVID-19 code of conduct below. This code will apply to any class that meets fully
or partially in an on-campus physical classroom for in-person instruction.
Violations: Refusal to comply with the COVID-19 code of conduct will be treated just
as any classroom disruption, which will receive request for immediate compliance,
failing which the student will be asked to leave the classroom. Any further
noncompliance will result in the dismissal of the entire class. All Covid-19 related
violations will be reported by the instructor to the Compliance Officer at Lally School,
and the Dean of Students. A student found to be in violation of the code, or required
repeated reminders for compliance, will be asked to participate in all classes remotely.
This is to protect their health and safety as well as the health and safety of their
classmates, instructor, and the university community.

Masks: All students must wear a mask in classrooms and all public places including
anywhere inside Pittsburgh building. Masks will be provided to the student by the
Institute.

Traffic Flow and Social Distancing: Students and faculty will respect the need for
social distancing. They are required to follow the traffic flow arrows posted in all rooms
and buildings, including bathrooms and common areas.

In-Class Seating: Students should sit in the appropriate designated seating in the
classroom. Students are not allowed to move furniture or sit in seats not designated by
the Institute.

Cleaning of Spaces: Students are encouraged to clean the surfaces of the

chairs/tables/desks they occupy before they sit down and as they prepare to leave.
Cleaning and sanitizing solutions will be provided the classroom.

Students who are ill, under quarantine for COVID-19, or suspect they are ill
should not come to class. All faculty will make every reasonable effort to
accommodate the student’s absence and will communicate that accommodation directly
to the student. Students who need to report an illness should contact the Student
Health Center via email or call 518-276-6287. For student seen off campus, a student
may request an excused absence via www.bit.ly/rpiabsence with an uploaded doctor’s
note that excuses them.

Syllabus 7 of 7 4.15.2021