Lecture1 - ML Introduction

CS-471: Machine Learning
Fall 2024
LMS Enrollment Code: 582196407
Dr Jameel Malik
muhammad.jameel@seecs.edu.pk
Today’s Outline
• Instructor
• Course Learning Outcomes (CLOs)
• Course Books
• Introduction to the Machine Learning

Instructor: Dr. Jameel Malik
• PhD from TU Kaiserslautern, Germany
– Area of expertise
• Machine Learning, Deep Learning and Computer Vision
• Re-joined NUST-SEECS in Spring 2021

– Subjects taught
• Advanced Computer Vision, Microprocessor Systems, Embedded
Systems.
• Office hours: through email

Course Learning Outcomes (CLOs)
 Interpret and discuss the fundamental concepts of machine learning in
its broad categories. (C2 Level)
 Implement and use core supervised and unsupervised algorithms to
solve key problems of signal processing and computer vision. (C3
Level)
 Analyze and select relevant machine learning approach for a given
challenge. (C4 Level)
 Remaining CLOs belong to labs (to be discussed by the Lab Engineer).

Course Books / Lecture Notes
 Class Lectures
 Coursera ML course by Andrew Ng.
 Pattern Recognition and Machine Learning by Christopher Bishop.

What is Machine Learning (ML)?
• AI: Intelligent systems that can learn and act autonomously.
• ML: enables machines to learn without explicit programming.
Machine Learning definition
• Arthur Samuel (1959). Machine Learning: Field of study
that gives computers the ability to learn without being
explicitly programmed.
• Tom Mitchell (1998) Well-posed Learning Problem: 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.
andrew ng
“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.”
Suppose your email program watches which emails you do or do
not mark as spam, and based on that learns how to better filter
spam. What is the task T in this setting?
Classifying emails as spam or not spam.
Watching you label emails as spam or not spam.
The number (or fraction) of emails correctly classified as spam/not spam.
None of the above—this is not a machine learning problem.
andrew ng
“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.”
Suppose your email program watches which emails you do or do
not mark as spam, and based on that learns how to better filter
spam. What is the task T in this setting?
Classifying emails as spam or not spam. (T)
Watching you label emails as spam or not spam. (E)
The number (or fraction) of emails correctly classified as spam/not spam. (P)
None of the above—this is not a machine learning problem.
andrew ng
A Few Examples of the State-of-the-art
Openpose
10
Machine Learning (ML)
• Supervised ML:
– The goal is to learn a mapping between input data and output data labels, so the
algorithm can make accurate predictions on new, unseen data.
• Unsupervised ML:
– The goal is to discover patterns, relationships, or structure in the data, without prior
knowledge of the output (unlabelled data).
Supervised ML: House Price Prediction
400
300
Price ($)
200
in 1000’s
100
0
0 500 1000 1500 2000 2500
Size in feet2
Supervised Learning Regression: Predict continuous

“right answers” given valued output (price)
andrew ng
Supervised ML: House Price Prediction
400
300
Price ($)
200
in 1000’s
100
0
0 500 1000 1500 2000 2500
Size in feet2
Supervised Learning Regression: Predict continuous

“right answers” given valued output (price)
andrew ng
Supervised ML
• Classification: Learns to predict a fixed

output (e.g. spam or not spam, type of
house).
house or townhouse?
Supervised ML vs. Unsupervised ML
• Given data labels • No data labels given
 Malignant Cancer  Malignant Cancer
 Benign Cancer  Benign Cancer
x2 x2
x1 x1 andrew ng
Supervised ML vs. Unsupervised ML
• Given data labels • No data labels given
 Malignant Cancer  Malignant Cancer
 Benign Cancer  Benign Cancer
x2 x2
Classification Clustering
Algorithm Algorithm
x1 x1 andrew ng
Unsupervised ML: News articles example
andrew ng
andrew ng
andrew ng
andrew ng
Of the following examples, which would you address using an
unsupervised learning algorithm? (Check all that apply.)
Given email labeled as spam/not spam, learn a spam filter.
Given a set of news articles found on the web, group them into
set of articles about the same story.
Given a database of customer data, automatically discover market
segments and group customers into different market segments.
Given a dataset of patients diagnosed as either having diabetes or
not, learn to classify new patients as having diabetes or not.
andrew ng

Lecture1 - ML Introduction

Uploaded by

Copyright:

Available Formats

Lecture1 - ML Introduction

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Lecture1 - ML Introduction

Uploaded by

Copyright:

Available Formats

CS-471: Machine Learning

• Course Learning Outcomes (CLOs)

• Introduction to the Machine Learning

• Re-joined NUST-SEECS in Spring 2021

• Office hours: through email

 Remaining CLOs belong to labs (to be discussed by the Lab Engineer).

 Coursera ML course by Andrew Ng.

 Pattern Recognition and Machine Learning by Christopher Bishop.

• Tom Mitchell (1998) Well-posed Learning Problem: A

Classifying emails as spam or not spam.

Watching you label emails as spam or not spam.

The number (or fraction) of emails correctly classified as spam/not spam.

None of the above—this is not a machine learning problem.

Classifying emails as spam or not spam. (T)

Watching you label emails as spam or not spam. (E)

None of the above—this is not a machine learning problem.

Supervised Learning Regression: Predict continuous

Supervised Learning Regression: Predict continuous

• Classification: Learns to predict a fixed

Given email labeled as spam/not spam, learn a spam filter.

You might also like