ML Lecture 1 Introduction and Policies
ML Lecture 1 Introduction and Policies
Learning
Faizad Ullah
1
About Me
Faizad Ullah
Ph.D. Student at LUMS
Specialization
Natural Language Processing (NLP)
Machine Learning
Data Science
Contributions
Medical Image Analysis
Graph Analysis
Text Analytics of Low-Resourced Language
2
Course Description
Theoretical (3 Credit Hrs Course)
Emphasis on hands-on and ML algorithms intuitions
3
Grading
Point distribution
Class Attendance and Participation 5%
Midterm 20%
4
Programming Tasks
*3-5 Assignments
Programming Assignments
*One Project
Programming Environment
Python (Pytoch, TensorFlow, Colab)
Plagiarism
Do NOT pass someone else’s work as your own!
Write in your own words and cite the reference if you use someone else’s material.
6
Policies (2)
Submission Policy
Submissions are due at the day and time specified
Late submissions will result in 50% marks deduction per day from obtained marks (i.e., 2 days
late submission will get zero credit).
Attendance Policy
You are advised to attend all lectures.
It’s the students’ responsibility to recover any information or announcements posted during a
lecture from which they were absent.
Classroom behavior
Maintain classroom sanctity by remaining quiet and attentive
Asking questions is encouraged.
You are not allowed to use a Laptop/mobile phone, etc., during class.
7
Policies (3)
Retakes
No retakes for quizzes, assignments, exams, or projects
In case of any medical emergency or unavoidable circumstances, inform before hand and seek a formal
approval. You need to share medical reports for departmental record.
Do not wait for the final exam to seek approval for retakes
8
Course Material
All course material (i.e.,Books, class handouts, reading
assignments) will be shared on Moodle
Text Book
Machine Learning: A Probabilistic Perspective, Murphy, Kevin P. MIT press, 2012 – Murphy.
The Elements of Statistical Learning: Data mining, Inference, and Prediction, Hastie, Trevor, Robert Tibshirani,
and Jerome Friedman, Springer Science & Business Media, 2009 – ESLII
Reference Book
Machine Learning, Tom Mitchell, McGraw Hill, 1997 – TM
9
Contact
How to contact me?
E-mail: Will share soon
Office:
Office Hours: Mentioned on office door
10
Most Important
12
We Imagine Machine Learning as…
13
ML is all around us…
14
Robots we Actual
Imagine
Robots 15
Robots Invasion We Imagine
16
Actual Invasion We Imagine
17
Why Discussing All This in ML Course?
A Broader understanding of Machine Learning
Although the focus of this course is concepts, mathematics, and implementation of machine
learning algorithms.
But you should know why we needed ML
What comes after we have learned ML
How are ML algorithms deployed in real-world applications
18
What is
Machine Learning?
How does it work?
19
Machine as Mechanical Helpers
20
Machines as Intellectual Helpers
21
Machines as Intellectual Helpers
Cat
No
Cat
{cat, dog}
happy
{happy, sad, angry,
surprised,
neutral}
23
A Classifier
empty
{empty, full}
Hospital
{Vocabulary of the
language}
24
A Classifier
Best Move
{Return the
best move}
Elon Musk
Names of People
25
A Classifier
26
How to train your intern?
How would you train a new intern to conduct job interviews?
27
How to train your intern?
How would you train a new intern to conduct job interviews?
Caveat!
What if the expert has systematic flaws of judgement aka biases?
◦ Conduct sessions with many experts
◦ What is they all share biases and stereotypes?
◦ Initially, your intern could only be as good as the expert
28
How to train your machine?
Allowing the machines to learn on their own, using prior decisions of experts is known as
Machine Learning!
Supervised Unsupervised
29
Artificial Intelligence VS ML
Colloquially both terms are used interchangeably
30
Life is not governed by certainty…
Certainty in the real-world is a rare luxury
Probability of something of being 0 or 1 is very rare!
Uncertainty is the basis of the ML that is quantified using probability and statistics
Something can and cannot happen with a certain probability!
31
Traditional Computer Science
Tasks like:
Play an audio/video file
Display a text file on screen
Perform a mathematical operation on two numbers
Sort an array of numbers using Insertion Sort
Search for a string in a text file
…
Data
Output
Program
32
Problems that Traditional CS Can’t Handle
Data
Output
Program?
33
Machine Learning
Regression
Classification
34
Traditional CS
Data
Output
Program
Machine Learning
Data
Program
Output
35
Machine Learning Pipeline
36
What is Machine Learning?
Formally:
A computer program A is said to learn from experience E with respect to some class of tasks T and
performance measure P if its performance at tasks in T, as measured by P, improves with experience E.
(Tom Mitchell, 1997)
Informally:
Algorithms that improve on some task with experience.
37
Data – Big, Big,… data!
How do we obtain these massive datasets to train our Machine Learning models?
From real interactions e.g., call centers
Expert annotators e.g., hired tams of annotators
Crowd sourcing
Recaptcha Tagging
38
Task-Label Relationship
Labels are dictated by the task to be performed.
Example: Speech Technologies
What was said? Speech Recognition
41
Challenges of ML – Fairness
AI tends to reflect the biases of the society
Human taggers who mark a recording as misinformation based on accent or gender
Court decisions in country that make a rich person’s acquittal more likely
Automated standardized testing in the US could yield unfavorable results for certain demographic
groups
AI plays a decision role in hiring decisions, with up to 72% of resumes in the US never being viewed by a
human (Automation Bias)
Decision on immigration, bank loans, credit history checks, criminal profiling
42
ML in Low-resource settings
Problems where large datasets and tools are not available
Natural Language Processing and Speech
Pakistan has 71 languages
We barely have speech recognition capabilities for Urdu!
43
The Offline Ones
3.6 billion people worldwide are offline
That is 46.6% of the world population
13.4% of the develop world, 53% of the developing world, and 80.9% of the Least Developed Countries
are offline*
Offline Populations
Too poor to afford internet-enabled devices
Too remote to access the internet
Too low-literate to navigate the mostly text-driven internet
44
References
Murphy Chapter 1
Alpaydin Chapter 1
TM Chapter 1
Lectures of Andrew Ng., Dr. Ali Raza, and “Machine Learning for Intelligent Systems
(CS4780/CS5780)”, Kilian Weinberger.
45