(Page 1 of 4)

COURSE: INF385T
COURSE TITLE: Introduction to Machine Learning

SEMESTER: Spring 2022

COURSE DESCRIPTION: Machine learning is all about finding patterns in data to get computers to solve
complex problems. In this course we study machine representations and algorithms that allow machines to
improve their performance on a defined task from experience. Instead of explicitly programming computers to
perform a task, machine learning lets us program the computer to learn from examples and improve over time
with or without human intervention. This requires addressing a difficult question: how to generalize beyond the
examples that have been provided at training time to new examples that you see at test time. This course will
show you how this generalization process can be formalized and implemented. We'll look at it from lots of
different perspectives, illustrating the key concepts in the field.

This course is a broad overview of existing methods for machine learning and an introduction to adaptive
systems in general. Emphasis is given to practical aspects of machine learning algorithms. The class format is
split between quizzes, assignments, and course project. Each class consists of a lecture session and in-class lab
session. The learning objective for each student is, once the student can understand the basics of machine
learning technology, and the close connection between theory and practice they will have the ability to apply it
to a wide range of applications in multiple fields.

COURSE PREREQUISITE (S): Python Programming.

RATIONALE: This course is intended to provide a foundation for all individuals who wish to pursue a career in
the field of applied Machine Learning or Data Science. Emphasis will be placed on learning the breadth of the
field with hand-on lab exercise for all the topics covered under this course.
ASSIGNMENTS: Students will have a total of 4 assignments in the first half of this course. Each assignment
description will be posted on the course website before the due date. They test students’ practical coding skills
to build, tune and evaluate ML algorithms discussed in class. Each assignment must be submitted before
11:59pm on its due date.
Late submissions policy: Each student will have 4 free “late days” to use during the semester. You can use
these late days to submit any assignment after the due date without any penalty. Assignments that are submitted
late, after exhausting the quota of late days will not be graded. A score of 0 will be given to that missing
submission.
QUIZ: There will be a total of 6 Quizzes that will be taken in-class during the last 15 minutes of the class hour.
The question on the quiz will be about the topic covered in class. Best 5/6 Quizzes will be considered toward
the 5% of total course grades.
PROJECT: The final class project will be due during the second half of the course. Details about each
submission will be posted on the course website prior to its deadline. The goal is to further develop students’
skills in conducting and communicating end-to-end solution to an open research problem.
Collaboration policy: Study groups are allowed, and students may discuss assignments in groups. However, we
expect students to understand and complete their own assignments. Each student must independently submit
their assignment and grading will be done based on the novelty of analysis and explanation. For the final course
project, students are expected to work in groups (2 students per group).
 (Page 2 of 4)

SUGGESTED TEXTBOOK (S) and/or MATERIALS:

 Hands-on Machine Learning with Scikit-Learn & TensorFlow: Concepts, Tools, and Techniques to
Build Intelligent Systems by Aurelien Geron

Programming experience is strongly recommended for this course. Please work through the following tutorial if
you do not have programming experience:

 Python Tutorial

COURSE GRADING: Grading the course will be calculated as follows:

% Breakdown of Final class Grade

Quiz 5%

Assignments 1 & 2 20% (10% each)

Assignments 3 & 4 30% (15% each)

Project 45%

COURSE ASSESSMENT MEASURES

OBJECTIVES
1. Understand the By the end of this course, students will be able to:
key concepts in  Identify potential applications of machine learning in practice.
machine learning.
 Describe the core differences in analyses enabled by regression, classification,
and clustering.
 (Page 3 of 4)
 Select the appropriate machine learning task for a potential application.

 Have the skills to apply regression, classification, clustering, retrieval,

recommender systems, and deep learning techniques to make data-driven
decisions.

 Represent your data as features to serve as input to machine learning models.

 Assess the model quality in terms of relevant error metrics for each task.

 Implement techniques in Python.

2. Propose machine Towards this aim, students will:

learning solutions to  Develop programming skills by writing code in Python
perform various
artificial intelligence  Experiment with machine learning libraries, including scikit-learn and
tasks. TensorFlow

 Be able to utilize Cloud Analytic Platform (Microsoft Azure)

 Evaluate machine learning algorithms for tasks in various application

domains, including for analyzing text and analyzing images

 Employ cloud computing resources to take advantage of modern hardware

and software platforms

3. Conduct and Towards this aim, students will:

communicate original  Propose a novel research idea (this will be an iterative process)
research.
 Design and execute experiments to support the proposed idea

 Write a research paper about the project (and possibly submit it for
publication)

 Present the project to the class

Class Topics Assignments/Quiz due dates

Python Programming Pre-Test posted
Jan 18th Course Introduction and Machine Learning Taxonomy
(Ungraded)
Python Programming Pre-Test
submission (Ungraded)
Jan 25th Statistics for Machine Learning
Quiz 1 in class ;
Assignment 1 posted
Assignment 1 submission;
Feb 1st Supervised ML: Regression Models
Assignment 2 posted
 (Page 4 of 4)
Quiz 2 in class;
Model Evaluation, Overfitting & Regularization of
Feb 8th Assignment 2 submission;
Learning Algorithms
Supervised ML:
Feb 15th Assignment 3 posted.
Support Vector Machines & Decision Trees
Quiz 3 in class;
Unsupervised Machine Learning & Reinforcement
Feb 22nd Assignment 3 submission
Learning
Assignment 4 posted
Mar 1st Recommendation Systems Assignment 4 submission
Machine Learning Pipelines
Mar 8th Enjoy Spring Break.
(Guest Lecture by Dr. Robert Dickerson)
Quiz 4 in class
Mar 22nd Introduction to Deep Learning & Neural Network Basics
Project Description Posted

Mar 29th Deep Neural Networks & Course Project Discussions

Quiz 5 in class
Apr5th Convolutional Neural Networks
Project Proposal Submission
Apr 12th Sequential Neural Networks
Quiz 6 in class
Apr 19th Natural Language Processing and Word embeddings
Midway Project Report Submission
Transformer Network Project Outline Submission
Apr 26th
(Guest Lecture by Dr. Jinfeng Rao) No Lab
Reading Day - No Class
May3rd
Work on Project Work and Presentations
Final Project Video
May10th Finals Week: 15 minute Project Presentations in class Code, and other project deliverables
submission deadline.