COSC 434

Introduction to Machine Learning

Professor Panos Liatsis

Department of Computer Science
D04208
Tel: 02-3123977
Email: [email protected]
Logistics

◼ Lecture slides
◼ Lecture slides to be covered in a class will be uploaded to
Blackboard LMS at least one day before the class.
 Textbook
❑ Textbook
❑ Stephen Marsland, Machine Learning: An Algorithmic
Perspective, Chapman & Hall/CRC, 2nd Edition, 2014. ISBN:
978-1466583283.
❑ Other useful books
❑ Aurélien Géron, Hands-On Machine Learning with Scikit-
Learn and TensorFlow: Concepts, Tools, and Techniques to
Build Intelligent Systems, O'Reilly Media, 1st Edition, 2017.
ISBN: 978-1491962299.
❑ Andreas C. Müller & Sarah Guido, Introduction to Machine
Learning with Python: A Guide for Data Scientists, 1st
Edition, O’Reilly Media, 2016. ISBN: 978-1449369415.
 Office Hours for Consultation
❑ Fixed time slots:
❑ Tuesdays 3-4pm and Thursdays 12-1pm
❑ Other time slots:
❑ send email for appointment
❑ Or, just come to my office to see me if I am around

❑ Venue:
❑ Dr. Panos’ office (D04208)
❑ MS Teams (during the online learning period)

Important: Please always put the tag [COSC434] in your email subject.

E.g. Subject: [COSC434] question on kNN

 Consultation
❑ You can consult the instructor during office hours.
❑ Before you seek help from the instructor, please make
sure that you:
➢ Attend the lectures and do the practical exercises
➢ Read the relevant sections of the book/lecture notes
➢ Try to understand the given materials
 Workload
❑ 3 credits course.

❑ You are expected to spend around 6 hours per

week independently working on this course,
outside the class and the lab.
 Assessment

Quizzes x 5 10%
Lab assignments 10%
Group project 30%
Semester Examination 20%
Final Examination 30%

❑ Late Submission Policy: For each homework, lab assignment, and

project, 10% of the earned score will be deducted for each late
day after the deadline.
 Exams
❑ Mid-term:
➢ Will be held on week 8.

❑ Final:
➢ Will be held on week 16.
➢ The final exam will include all the topics taught
throughout the semester (i.e., from the beginning to
the end).
 Attendance
❑ The instructor has to report the students’
attendances (after the add/drop period).

❑ According to the University Policy

❑ 5 minutes late is absent
❑ 80% attendance or less is failure

❑ Mobile phones are requested be on silent mode or

switched off.
 Plagiarism
❑ The university has a zero tolerance policy to
plagiarism in homework, lab assignments,
project, and exams.
Please Answer the Survey.
◼ Blackboard -> Content
◼ Go to “COSC434 Survey”
◼ Please download the .docx file and fill in
your answers.
◼ Please upload your answer file by
2/9/2024.
◼ Thank you!
 Machine Learning

The materials are adopted from the book: Aurélien Géron, Hands-On
Machine Learning with Scikit-Learn & TensorFlow, O’Reilly Media, 2017.
Goals of this course
❑ Learn basic theories of machine learning.
❑ Learn to use machine learning algorithms to
perform key operations such as preprocessing,
regression, classification, clustering, visualization.
❑ Learn how to evaluate machine learning
algorithms.
❑ Gain hand-on experience on Python data
analytics and machine learning environment.
What is machine learning?
◼ Machine Learning is the science (and art) of
programming computers so they can learn from data.
◼ Here is a slightly more general definition:
◼ [Machine Learning is the] field of study that gives computers
the ability to learn without being explicitly programmed. —
Arthur Samuel, 1959
◼ And a more engineering-oriented one:
◼ A computer program is said to learn from experience E with
respect to some task T and some performance measure P, if
its performance on T, as measured by P, improves with
experience E. —Tom Mitchell, 1997
 Example
◼ For example, your spam filter is a Machine Learning program that
can learn to flag spam given examples of spam emails (e.g.,
flagged by users) and examples of regular (nonspam, also called
“ham”) emails.
◼ The example data that the system uses to learn are called the
training set. Each training example is called a training instance (or
sample).
◼ Here, the task T is to flag spam for new emails, the experience E
is the training data, and the performance measure P needs to be
defined;
◼ E.g., you can use the ratio of correctly classified emails. This particular
performance measure is called accuracy and it is often used in classification
tasks.
Why use machine learning?
◼ Traditional way – rule-based
1. You would look at what spam typically looks like. You
might notice that some words or phrases (such as “4U,”
“credit card,” “free,” and “amazing”) tend to come up a lot
in the subject. Perhaps you would also notice a few other
patterns in the sender’s name, the email’s body, and so on.
2. You would write a detection algorithm for each of the
patterns that you noticed (using a lot of nested if .. else
statements), and your program would flag emails as spam
if a number of these patterns are detected.
3. You would test your program, and repeat steps 1 and 2
until it is good enough.
Traditional rule-based approach
Weakness of rule-based
approach
◼ It was popular in 1970’s and 1980’s.
◼ A lot of so-called Expert Systems were rule-
based.
◼ The major drawback:
◼ Since the problem (like spam filtering) is not
trivial, your program will likely become a long
list of complex rules—needs to be updated
frequently and pretty hard to maintain.
Machine Learning Approach
◼ In contrast, a spam filter based on Machine
Learning techniques automatically learns which
words and phrases are good predictors of spam by
detecting unusually frequent patterns of words in
the spam examples compared to the ham
examples.
◼ The program is much shorter, easier to maintain,
and most likely more accurate.
Machine Learning Approach
Machine learning approach is
flexible.
◼ If spammers notice that all their emails containing
“4U” are blocked, they might start writing “For U”
instead.
◼ A spam filter using traditional rule-based techniques
would need to be updated to flag “For U” emails.
◼ If spammers keep working around your spam filter,
you will need to keep writing new rules forever.
◼ In contrast, a spam filter based on Machine Learning
techniques automatically notices that “For U” has
become unusually frequent in spam flagged by users,
and it starts flagging them without your intervention.
Machine learning approach is
flexible.
 Machine learning is useful for
highly complex problems.
◼ Machine learning is the best solution for problems that
either are too complex for traditional approaches or have
no known algorithm.
◼ For example, consider speech recognition: say you want to start
simple and write a program capable of distinguishing the words
“one” and “two.” You might notice that the word “two” starts with
a high-pitch sound (“T”), so you could hardcode an algorithm that
measures high-pitch sound intensity and use that to distinguish
ones and twos.
◼ Obviously this technique will not scale to thousands of words
spoken by millions of very different people in noisy environments
and in dozens of accents.
◼ The best solution (at least today) is to write an algorithm that
learns by itself, given many example recordings for each word.
Machine Learning can help
humans learn!
In summary
◼ Machine Learning is great for:
◼ Problems for which existing solutions require a lot of hand-
tuning or long lists of rules: one Machine Learning algorithm
can often simplify code and perform better.
◼ Complex problems for which there is no good solution at all
using a traditional approach: the best Machine Learning
techniques can find a solution.
◼ Fluctuating environments: a Machine Learning system can
adapt to new data.
◼ Getting insights about complex problems and large amounts
of data.
Topics related to machine
learning
◼ Machine learning is generally viewed as a
sub-discipline of “artificial intelligence (AI)”.
◼ It is related to and/or have overlaps with the
other sub-disciplines of AI.
◼ Data analytics
◼ Data mining
◼ Data Science
◼ Robotics
◼ Computer vision
Python Installation
◼ Anaconda
◼ https://www.anaconda.com/products/individual
Reminder Request
◼ Please answer the survey (in
Blackboard’s Content) by 20/01/2023.
Questions?