0% found this document useful (0 votes)
82 views

New York University Tandon School of Engineering: Baris - Coskun@nyu - Edu)

This document provides an overview of a machine learning course offered at NYU Tandon School of Engineering in Fall 2021. The course will cover major machine learning concepts and methods through programming assignments and a final project. Students will learn techniques like logistic regression, support vector machines, decision trees, Bayesian learning, and ensemble methods. The course will be conducted online, with lectures, weekly discussions, assignments, and a final project. Students are expected to spend 6-8 hours per week on asynchronous work and synchronous meetings.

Uploaded by

Pramod Bhat
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
82 views

New York University Tandon School of Engineering: Baris - Coskun@nyu - Edu)

This document provides an overview of a machine learning course offered at NYU Tandon School of Engineering in Fall 2021. The course will cover major machine learning concepts and methods through programming assignments and a final project. Students will learn techniques like logistic regression, support vector machines, decision trees, Bayesian learning, and ensemble methods. The course will be conducted online, with lectures, weekly discussions, assignments, and a final project. Students are expected to spend 6-8 hours per week on asynchronous work and synchronous meetings.

Uploaded by

Pramod Bhat
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

New York University Tandon School of Engineering

Machine Learning
CS-GY-6923/ECE-GY-6143
Fall 2021

Instructor: Baris Coskun ([email protected])

Course Pre-requisites
Basic understanding of probability, linear algebra, and computational algorithms. Basic
facility in programming in Python.

Course Description
This online course is aimed at developing practical machine learning and data science
skills. The course will cover theoretical basics of broad range of machine learning concepts
and methods with practical applications to sample datasets via programming assignments.

Course Objectives
By the end of this course students should be able to:
• Describe the principal models used in machine learning and the types of problems to which
they are typically applied.
• Compare the assumption made in each model and the strengths and weakness of each
model.
• Determine to which problems machine learning is applicable and which model or models
would be most appropriate in each case.
• Apply the principal models in machine learning to appropriate problems

Course Structure
• This course is conducted entirely online, which means you do not have to be on campus to
complete any portion of it.
• You will participate in the course using NYU Brightspace located at
https://brightspace.nyu.edu/.
• Lectures will become available at midnight each week and will be delivered through Active
Learning Modules* in NYU Brightspace.
• In addition to lectures, participation will play a key role in this course. Students are
expected to participate in weekly discussion forums and webinar sessions.

Grade Breakdown (%)


• Weekly Assignments: 40%
• Engagement (forums and virtual sessions): 20%
• Final Project: 40%

*Consult with NYU Tandon Online for further details about Active Learning Modules.
Learning Time Rubric

Learning Time Asynchronous* / Time on Task Notes


Element Synchronous** for Students
(weekly)
Video format. Expect quizzes
Lecture Asynchronous 2 hours
throughout the module.
Students are expected to post initial
Weekly
Asynchronous 1 hour response to weekly topic questions.
Discussion Board
See Interaction Policy.
Programming Students submit their assignment by
Asynchronous 2 hours
Assignment the specified date.
Project Asynchronous 1 hour
Reading
Asynchronous 2 hours Reading assigned textbook chapter
Assignment

*Asynchronous learning is defined as any non-real time student learning, such as recorded lecture, podcast, interactive module,
articles, websites, etc. This also includes any student-to-student or faculty-to-student communication that may happen with an
asynchronous tool, such as discussion board, chatroom, e-mail, text, etc.
**Synchronous learning is defined as any real-time student-to-student and/or faculty-to-student learning, such as a live webinar
session or other video/audio communication service.

Course Communication

Announcements -

Announcements will be posted on NYU Brightspace on a regular basis. You can locate all class
announcements under the Announcements tab of our class. Be sure to check the class
announcements regularly as they will contain important information about class assignments and
other class matters.

Email –

You are encouraged to post your questions about the course in the Forums discussions on NYU
Brightspace. This is an open forum in which you and your classmates are encouraged to answer
each other’s questions. But, if you need to contact me directly, please email me at
[email protected]. You can expect a response within 48 hours.

Weekly Discussion Forums –

Discussion forums are an excellent way for you to engage with the course material and with your
peers. Each module will have an accompanying discussion board question posted in the Forums
tab. You are expected to read the discussion boards and engage in thoughtful discussions. I will
read all discussion posts and provide content clarification and feedback when necessary.
Weekly Virtual Meetings –

Once a week, we will hold a virtual class meeting through the Meetings tool on NYU Brightspace.
This weekly meeting is an opportunity for you to ask questions and gain clarification about the
course content from myself and your peers. You are highly encouraged to attend these meetings. I
understand that not all students will be available to attend these virtual meetings. Due to this fact,
the meetings will be recorded so you can watch them when you are available.

Netiquette –

When participating in an online class it is important to interact with your peers in an appropriate
manner. Always use professional language (no netspeak) in your discussion board posts and
emails. Please be respectful of your classmates at all times even if you disagree with their ideas.

Interaction Policy

You are required to be an active online learner in this course and expected to participate in the
Active Learning Modules, weekly discussion boards, weekly virtual meetings

Readings
The required texts for the course are
1. Introduction to Machine Learning, Third Edition, Ethem Alpaydin, MIT Press, 2014
2. Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-
learn, and TensorFlow 2, Third Edition, Sebastian Raschka and Vahid Mirjalili, Packt
Publishing, 2020.

You can access NYU’s central library here: http://library.nyu.edu/


You can access NYU Tandon’s Bern Dibner Library here: http://library.poly.edu/

Course requirements

Participation is paramount to your success in this course. Be sure to log into NYU Brightspace
multiple times a week, read all announcements, complete all Active Learning Modules and
assignments on time, and participate in Discussion Forums and Virtual Meetings.

Topics

Topic 1: Introduction to the course and to machine learning


• Objective: Be able to describe, at a very high level, what machine learning is and
why it is becoming increasingly prevalent.
• Readings: Alpaydin, Chapters 1 and 2. Read for the big picture. Don’t get stuck on
the details.
• Discussion Forum: Introductory post about yourself.
• Webinar Session
• Programming Assignment: Set up your Jupyter notebook environment.
Topic 2: The Perceptron and Adaline machine learning models
• Objectives: Be able to describe and implement the Perceptron and Adaline machine
learning models. Be able to compare the assumptions of these two models and
discuss their strengths and weaknesses.
• Reading: Alpaydin, Ch. 11.1 - Ch. 11.4
• Reading: Raschka, Ch 2., pp 1-50; Ch 3., pp 51-58.
• Discussion Forum
• Webinar Session
• Programming Assignment 2.

Topic 3: Logistic regression model, regularization. Multiclass classification


• Objectives: Be able to describe and implement the logistic regression machine
learning model. Be able to describe regularization, determine to which machine
learning situations it is applicable, and apply it. Be able to apply binary
classification models to multiclass problems.
• Reading: Alpaydin, Ch. 10
• Reading: Raschka, Ch 3. pp 51-58.
• Discussion Forum
• Webinar Session
• Programming Assignment 3

Topic 4: Support Vector Machines and Kernel Machines


• Objectives: be able to
• Describe the support vector machines and kernel machines.
• Implement SVM and kernel machine learning models.
• Reading: Alpaydin, Ch. 10
• Reading: Raschka, Ch 3, pp. 76-87.
• Discussion Forum
• Webinar Session
• Programming Assignment 4

Topic 5: Decision Trees and Decision Tree Pruning


• Objectives: Be able to describe and implement the decision tree machine learning
model and to determine when pruning is appropriate and, when it is appropriate,
implement it.
• Reading: Aplaydin Ch. 6 and Ch. 9.
• Reading: Raschka, Ch 3, pp. 88-97.
• Discussion Forum
• Webinar Session
• Programming Assignment 5
Topic 6: Bayesian Learning
• Objective: Be able to describe and implement Bayesian machine learning models.
• Reading: Alpaydin, Ch. 3.
• Discussion Forum
• Webinar Session
• Project description

Topic 7: Ensemble Methods


• Objectives: Be able to describe the difference between strong and weak
learnings. Be able to describe the techniques of bootstrapping, gradient
boosting, and Adaboosting. Be able to describe and implement the random
forest machine learning model.
• Reading: Alpaydin, Ch 17.
• Reading: Raschka, Ch. 7.
• Discussion Forum
• Webinar Session
• Programming Assignment 7

Topic 8: Regression
Objectives: Be able to describe how to use multiple machine learning models to solve regression
problems and to implement these techniques.
• Reading: Alpaydin, Chs. 7, 8.
• Reading: Raschka, Ch. 10, Ch. 11.
• Discussion Forum
• Webinar Session
• Programming Assignment 8.

Topic 9: Clustering and Nonparametric Models including PCA. Dimensionality Reduction


Objectives: Be able to describe and implement clustering and nonparametric models.
• Reading: Alpaydin, Chs. 7, 8.
• Reading: Raschka, Ch. 10, Ch. 11.
• Discussion Forum
• Webinar Session
• Submit Project Topic

Topic 10: Neural Networks and Backpropagation


• Objective: Be able to describe the technique of backpropagation. Be able to
describe and implement machine learning models based on neural networks
• Reading: Alpaydin, Ch 11.5 - Ch. 11.13.
• Reading: Raschka, Ch. 12.
• Discussion Forum
• Webinar Session
Topic 11: Other topics in Neural Networks
• Objective: Be able to describe and implement techniques utilizing convolutional
neural networks, recurrent and recursive neural networks, and hidden Markov
models.
• Reading: Alpaydin Ch 15
• Discussion Forum
• Webinar Session

Topic 12: Reinforcement Learning


• Objective: Be able to describe and implement reinforcement learning machine
learning techniques.
• Reading: Alpaydin, Ch 18.
• Discussion Forum
• Webinar Session
• Submit Project Report Draft

Topic 13: Generative Adversarial Networks, Ethics and Fairness in Machine Learning, and
Concluding Comments
• Be able to describe Generative Adversarial Networks. Be able to describe ethical
and fairness issues in machine learning.
• Reading: Arvind Narayanan, Twenty one definitions of fairness and their policies,
ACM FAT* 2018, https://www.youtube.com/watch?v=jIXIuYdnyyk
• Reading: Moritz Hardt, Eric Price, and Nathan Srebro, Equality of opportunity in
supervised learning, 2016.
• Discussion Forum
• Webinar Session

Topic 14: Presentation of Final Projects

Moses Center Statement of Disability

If you are student with a disability who is requesting accommodations, please contact New York
University’s Moses Center for Students with Disabilities (CSD) at 212-998-4980 or
[email protected]. You must be registered with CSD to receive accommodations. Information
about the Moses Center can be found at www.nyu.edu/csd. The Moses Center is located at 726
Broadway on the 2nd floor.

NYU School of Engineering Policies and Procedures on Academic Misconduct (from the
School of Engineering Student Code of Conduct)

1. Introduction: The School of Engineering encourages academic excellence in an environment


that promotes honesty, integrity, and fairness, and students at the School of Engineering are
expected to exhibit those qualities in their academic work. It is through the process of
submitting their own work and receiving honest feedback on that work that students may
progress academically. Any act of academic dishonesty is seen as an attack upon the School
and will not be tolerated. Furthermore, those who breach the School’s rules on academic
integrity will be sanctioned under this Policy. Students are responsible for familiarizing
themselves with the School’s Policy on Academic Misconduct.

B. Definition: Academic dishonesty may include misrepresentation, deception, dishonesty, or


any act of falsification committed by a student to influence a grade or other academic
evaluation. Academic dishonesty also includes intentionally damaging the academic work of
others or assisting other students in acts of dishonesty. Common examples of academically
dishonest behavior include, but are not limited to, the following:

1. Cheating: intentionally using or attempting to use unauthorized notes, books,


electronic media, or electronic communications in an exam; talking with fellow
students or looking at another person’s work during an exam; submitting work
prepared in advance for an in-class examination; having someone take an exam for
you or taking an exam for someone else; violating other rules governing the
administration of examinations.
2. Fabrication: including but not limited to, falsifying experimental data and/or
citations.
3. Plagiarism: intentionally or knowingly representing the words or ideas of another as
one’s own in any academic exercise; failure to attribute direct quotations,
paraphrases, or borrowed facts or information.
4. Unauthorized collaboration: working together on work that was meant to be done
individually.
5. Duplicating work: presenting for grading the same work for more than one project or
in more than one class, unless express and prior permission has been received from
the course instructor(s) or research adviser involved.
6. Forgery: altering any academic document, including, but not limited to, academic
records, admissions materials, or medical excuses.
Access the entire School of Engineering Student Code of Conduct here:
engineering.nyu.edu/academics/code-of-conduct

You might also like