Course Code: CS001B2

Ayush Singh

Spring, 2022

E-mail: [email protected]
Office: Remote Class Room: Live, Zoom

Lab Room: Zoom

Course Description
In this course, you will get to learn machine learning topics in-depth, it covers both the aspects
practically, mathematically. You will learn in-depth mathematics behind algorithms and you will
implement these algorithms, techniques from scratch as well. We start by covering up mathe-
matics review part which are required for successfully completing this course such as calculus,
linear algebra, probability theory and we are not only covering wide-range of theory, we are also
covering various case studies, machine learning system design, good resume level projects taken
from kaggle competitions that solves real world problems, large scale machine learning and lot
more. See the course page for more information.

Required Materials
• Course Notes, Lecture Slides, Lecture Schedules, Lecture recordings will be available at
your LMS.

• This course does not follows any Textbook, but we will be adding some texts book in
resources.

Prerequisites/Corequisites
Prerequisites: Python

Course Objectives
Successful students:

1
 CS001-B02

1. Students will master machine learning algorithms and apply these algorithms in real world
taking care of pros and cons of an algorithm.

2. Students will learn to apply machine learning into a real world problem, by following the
full machine learning pipeline like data ingestion, processing and etc.

3. Student will be able to understand and explain the in-depth mathematics behind machine
learning algorithms, techniques.

4. Students will be confident in sitting for an interview for Machine Learning Engineering Or
Data Scientist Role.

5. Students will also master advance machine learning concepts such as Learning Theory,
Factor Analysis, and lot more.

6. Students will be able to design their own machine learning systems in real world, they will
be able think about problem from various point of views.

7. Students will get to learn about debugging machine learning applications, deployment
process like blu green deployment, canary deployment.

8. Students will be able to do kaggle competitions, work on complicated machine learning

projects confidently whether it be alone or in a team.

9. Students will also get career advices from various experts who have done PHD’s, Worked
in Top MNC’s like Google, Facebook and have 17+ YOE and lot more.

10. Students will also get to know about recent trends like MLOps, Data Centric AI and a lot
more.

11. Students will also get to know about how big companies uses machine learning in building
their products.

12. Students will be getting separate interview problems and mock interviews to prepare them
for an interview.

Course Structure
Class Structure
• Lectures(2 Live Lectures/Week ):- These types of lectures are mainly theoretical lectures
which teaches you the theory, concepts, and etc by the lead lecturer of the course. Each live
lecture will be of 2 - 2.5 hours according to the complexity of the topic. Live Lectures will
be on Zoom and It will be recorded and will be uploaded to the lms within 5 hours.

• Recitation Lectures(1-2 Live/Recorded Recitation Lectures/Week):- In recitation session,

Ta’s or main lecturers will walk you through some questions based on the topics which is
taught in the main lectures. These recitation lectures can be live or recorded.

2/7
 CS001-B02

• Lab Session(1 Live Lecture/Week):- In these types of lectures, students will be guided
through real world projects, these kind of projects are basically taken from past kaggle
competitions or big hackathons that solves real world problems, these projects follow the
full data science pipeline and they are made in such a way that any machine learning
applications are made in production.

• Guest Lectures(15 Hours of Guest Lectures):- Guest Lecturers will give you career advice,
they will talk about machine learning system design, Machine learning in Production, In-
terview preparation, Career Paths, decision making, NLP,Computer Vision and etc.

Assessments
• Homework Assignment:- Per week a Homework assignment will be released, The home-
work assignment usually contains some problems which are theoretical, mathematical
problems and lot more.

• Programming Assignment:- You will get programming assignment every week, the pro-
gramming assignment are auto graded, programming assignment are released through
grade scope and you will be notified via lms.

• Project Proposal:- Project Proposals are the projects that are done in a team or being alone
and writing a proposal and building up a poster for every project.

Final Exam and Class Project

1. Mid-Term Project Proposal

2. Final-Term Project Proposal

Note:- A brief info about this can be found here.

Grading Policy
The typical NC State grading scale will be used. I reserve the right to curve the scale dependent
on overall class scores at the end of the semester. Any curve will only ever make it easier to obtain
a certain letter grade. The grade will count the assessments using the following proportions:

• 50% of your grade will be determined by your mid-term and final term exams (25% each).

• 48% of your grade will be determined by your homework problems and coding question.

• 3% of your grade will be determined by your attendance, discussions, engaging in the

question, being active.

3/7
 CS001-B02

Course Policies
During Class
For smooth, engaging, full of learning, we have some rules to be followed during the classes:-
• If you Enter in the class, Make sure your Camera is turned Off, we are doing this because we highly care about
privacy, safety about the particular student.
• You will get your Unique Student ID, When you enter in the class, your username should be named as FULL
NAME | ID.
• We highly encourage you to participate in-class polls, fun activities and collab as it will have a great impact on
you.
• We ask you to keep your mic muted if you’re not speaking as it will prevent some background noise from your
side, but we encourage you to speak up in class if you want to add on something, or you want to ask questions,
or just want to share some of your insights.
• We encourage students to ask questions if they get in a class, you ca raise your hand or just unmute and speak
up.
• We highly encourage students to re-watch the recording of the class, and make your own notes for this course.
We will give you lecture notes for sure but still we recommend this to do.

Attendance Policy
We understand that you’re not available every time to attend the class in-live, but we are taking attendance seriously
as we need to ensure which student are learning and which or not. In live sessions, you will be given code that
you have to make use to mark your attendance, the code will be the access code of the lecture quiz that you have to
answer, quiz will be based on the lecture, if you pass the quiz with full marks then you get full attendance otherwise
no attendance, so if you’re watching recording you will be also having access code, you can also use it and each access
code have some deadline or the quiz has some deadline, you have to make sure that you complete the attendance
quiz before the deadline, you will be most likely not able to attempt the quiz after the deadline and you will loose
your credit.

Submitting Assignments
To limit access to the assignments to only enrolled students and to avoid having the solutions show up online publicly,
the assignments will only be posted on Piazza and your LMS. Assignments will be submitted through Gradescope.
You will receive an invite to Gradescope for CS001-B01 Machine Learning Engineering 2022. If you have not received
an invite email after the first few days of class, if not please post a private message on piazza for us to add you. All
assignments must be submitted individually.
This quarter, we are allowing pair submissions for homeworks. You may submit solo or with a partner (in which
case please submit only once on Gradescope, and add their name). This is unrestricted; you may do some or all
assignments solo, or with the same (or different) partners.
If you work with a partner, you must be sure you both understand all written material / code submitted. Don’t
just divide up the work; this will potentially put you at a disadvantage on the midterm and elsewhere in your AI/ML
career! We strongly recommend working through each problem together.
Regardless of whether you work solo or with a partner, you may discuss the homeworks at a high level with other
students in the class. Talking through approaches is OK, but you may not e.g. directly trade answers; in particular,
you must not look at any written work or code from anyone but your partner (if any).

Late Assignments Policy

Each student will have a total of three free late (calendar) days to use for homeworks and the project proposal and
milestone. Students cannot use late days on the project final report or poster. Once these late days are exhausted, any
assignments turned in late will be penalized 20% per late day. However, no assignment will be accepted more than
three days after its due date. Each 24 hours or part thereof that a homework is late uses up one full late day. Please
note that late days are applied individually.

4/7
 CS001-B02

Academic Integrity and Honesty

We strongly encourage students to form study groups. Students may discuss and work on homework problems in
groups. However, each student (or pair of students, if submitting as a pair) must write down the solution indepen-
dently. Each student must understand the solution well enough in order to reconstruct it by themself. It is an honor
code violation to copy, refer to, or look at written or code solutions from a previous year, including but not limited to:
official solutions from a previous year, solutions posted online, and solutions you or someone else may have written
up in a previous year. Furthermore, it is an honor code violation to post your assignment solutions online, such as
on a public git repo. We run plagiarism-detection software on your code against past solutions as well as student
submissions from previous years.

Copyright and Sharing Materials Policy

All curriculum for this course, including but not limited to lecture slides and recordings, lab materials, and homework
assignments are the copyrighted property of The Coding School. You are not allowed to circulate the materials to
students outside of the course.

Student Safety and Privacy

We take student safety and privacy seriously. All instructional staff have undergone background checks and par-
ticipated in sexual harassment training. Instructors and TAs have all been sourced from personal and professional
networks and come recommended.

All students are required to agree to the Code of Conduct as a condition of enrolling in the program. To read our
comprehensive Code of Conduct, please click here.
Antern Learning takes Code of Conduct violations seriously. Depending on the severity of the concern, violations
may result in immediate dismissal from the course.

To report a Code of Conduct violation, please fill out the form here. For urgent matters, email us with the subject line
‘URGENT’ at email.

Data Privacy Policy

To view The Antern’s Learning data privacy policy, click here. To summarize, Antern Learning does not sell, share,
or distribute participants’ data to third parties.

5/7
 CS001-B02

Schedule and weekly learning goals

The schedule is tentative and subject to change. The learning goals below should be viewed as the key concepts you
should grasp after each week, and also as a study guide before each exam, and at the end of the semester. Each exam
will test on the material that was taught up until 1 week prior to the exam (i.e. vorticity will not be tested until exam
2). The applications in the second half of the semester tend to build on the concepts in the first half of the semester
though, so it is still important to at least review those concepts throughout the semester.

Week 01, 01/08 - 01/12:

• Linear Algebra and Analytical Geometry
• Calculus:- Differentiation and Integration
• Probability Theory Statistics
• Numpy, Pandas, Matplotlib

Week 02, 01/15 - 01/19:

• Introduction to machine learning
• Probability Theory Statistics
• Supervised Learning:- Linear Regression
• Exploratory Data Analysis - Project

Week 03, 01/22 - 01/26:

• Supervised Learning:- Linear Regression
• Logistic Regression Intro to GLM’s
• Concrete Strength Prediction - Project
• New York City Taxi Fare Prediction - Project ( Starting )

Week 04, 01/29 - 02/02:

• Generalized Linear Model Regularization
• Naive Bayes, Kernel Methods
• Quora Insincere Questions Classification - Project ( starting )

Week 05, 02/05 - 02/09:

• Support Vector Machine
• Learning Theory DT Introduction
• Quora Insincere Questions Classification - Project ( Improving and Completing it!! )

Week 06, 02/12 - 02/16:

• Ensemble Learning : Bagging Boosting
• Unsupervised Learning Part - 1
• Production Grade Credit Card Defaulters System - Project
• Production Grade Personalized Cancer Diagnosis - Project

Week 07, 02/19 - 02/23:

• Hierarchical Clustering Anomaly Detection
• Recommendation System
• Production Grade Customer Segmentation - Project
• Building a Recommendation System Setting in Unsupervised Learning

6/7
 CS001-B02

Week 08, 02/26 - 03/02:

• Deep Learning
• Natural Language Processing
• GNN’s
• GANS and Computer Vision

Week 09, 03/05 - 03/09: Guest Lectures

• Winning Data Science Competitions
• Large Scale Machine Learning Deployment
• ML-Ops ( ML In Production )
• Giving ML Interview
• Resume Building, Communication, Impressing, Take Home Challenge

Course Tech On boarding

1.) Setup your LMS
• Step 1:- Go at this link:- https://antern.neolms.com/
• Step 2:- Click on Sign up and Click On "Write your Access Code". Your Access code is iamstudent
• Step 3:- Create your Account
• Step 4:- After you created your account, now you have to enroll in CS001 for that click on classes from the ham
menu and then click on Enroll and it will ask you a code, give the code as ZLAJ-JDZC
• See this Guide by NEO:- https://www.neolms.com/docs/neo/NEO-Students-Guide.pdf
Warning:- You don’t have to share your access code to anyone, If you share it then other people can enroll in this,
So please don’t share if shared, we can make you drop from the course.

2.) Setup your Gradescope

We will use Grade Scope for assignment submission and grading stuff. You Should Have received the Invitation, If
not please reply back! If you haven’t received the grade scope invitation please do email Ayush Singh.
3.) Piazza
We will use Piazza for discussions, technical problems, or help needs, so here are the steps for this:-

• Step 1:- piazza.com/antern/spring2022/cs001

• Step 2:- Select CS001 and it will ask Access Code, Your Access Code is cs001b02.
• Step 4:- Create Your Account and You’re in!

4.) Zoom Links

We will use Zoom for Online classes. We will send you zoom online classes as well as labs link, all the schedules will
be sent to you via email. And Finally You’re done for your Enrollment in this course!

5.) Discord
Join the Antern community server here (https://discord.gg/Afj5M3cp).You will be having access to the private chan-
nels as well. After you get into the server, DM Ayush Singh, He will give you a tag of cs001 students and then you
will have access to some private channels made for you.

6.) Whatsapp
You can join our group specifically made for this batch for your general chit chat and questions which yuo can join
from here (https://chat.whatsapp.com/KYJFBZj4YIL3ARCMhEj0LA). See the starred message for rules which you
have to follow.

7/7