CPSC 322: Introduction to

Artificial Intelligence
Lecture 01: Course Overview
Mehrdad Oveisi
Adapted from slides by Cristina Conati, Giuseppe Carenini,
Varada Kolhatkar, and Jordon Johnson

1
About Me
• Mehrdad Oveisi
• [email protected]
• For most of course related requests, please use Piazza or [email protected]
• linkedin.com/in/oveisi

• B.Sc., M.Sc., Ph.D., all in Computer Science

• Ph.D. in AI
• Belief Revision (logical approach)
• Research in AI and applications of AI/ML in biomedical domains

• Horrible at remembering names…

• So, I don’t mind if you forget mine!
2
Mics. points to keep in mind
• More emphasis on conceptual understanding than memorization

• Sometimes lecture slides leave things underspecified

• E.g., solve a problem without providing precise steps or formatting instructions
• This is usually intentional
• Important convention/notation/formatting are usually well specified
• The lecture slides have examples you can review

• The best answers are

• correct
• easy to read
• as short as possible, while including important information
• note that penalties may be applied for irrelevant information
3
Icebreaker Activity

Introduce yourselves to the people next to you:

• What program are you in?

• Why are you taking this course?

• What is one weird and/or fun thing about you?

4
Scope of This Course
This course is very much an introduction to AI (as the name implies)
• AI is an immense field
• We’ll be looking at types of problems and environments agents
may need to deal with
• We will discuss several approaches to handle these problems
• help prepare you for more in-depth approaches later (e.g., 422)

Machine learning (ML) techniques are very useful for a number of

problems in AI, but those are covered in courses like CPSC 330 & 340
5
Course Prerequisites

• Prerequisite course: CPSC 221

• This implies you’ve also taken CPSC 121 and CPSC 210 (or equivalent)

• Assumptions:
• You understand the material in all prerequisite courses
• You have developed some skill in:
• Reading and understanding code/pseudocode/algorithms
• Implementing pseudocode/algorithms/formulas/concepts/etc.
• Solving problems without explicitly being told exactly how
• You know or you’re interested to know Python! (see AIPython.org)
6
Big Picture – CPSC 322
Environment

Problem Deterministic Stochastic

Variables + Constraints
Constraint Search
Satisfaction Arc Consistency
Static Local Search
Logics Bayesian (Belief) Networks
Query
Search Variable Elimination
STRIPS Decision Networks
Sequential Planning
Search Variable Elimination

Representation
Reasoning Technique

7
Course Essentials

• Lectures:
• Each lecture will contain a set of learning goals
• Slide header colors indicate function:
Administrative / Logistics
In-class Activity
Recap from Previous Slide Decks
Aside / Not Examinable
(No color) Regular Course Content
8
Course Essentials
• Textbook: selected chapters from
Artificial Intelligence, 2nd Edition, by Poole and Mackworth
• https://artint.info/2e/html/ArtInt2e.html
• freely available online, no need to buy anything
• 3rd edition has also been released, which is freely available online as well
• https://artint.info/3e/html/ArtInt3e.html
• Feel free to explore the corresponding content in the new edition

• Optional Reference:
Artificial Intelligence: A Modern Approach, 4th Edition, by Russell and Norvig
• http://aima.cs.berkeley.edu/
• Copies may be available in CS reading room

9
Course Essentials

• Course content will be found on Canvas

• Course policies
• Lecture slides and other resources
• Scheduling information
• Additional review materials

• On PrairieLearn (PL):
• Assignments
• Exams
10
Course Essentials
• Piazza
• discussion board
• course announcements
• use Piazza for questions about course material, assignments, logistics, etc.
• use email for private questions (eg. grade inquiries or health issues)
• iClicker Cloud
• used for in-class quizzing/polling
• we are no longer using physical iClickers
• Tools for learning AI concepts
• AISpace.org: written in Java
• AIPython.org: next generation, and in Python!
• Both developed here at UBC :-)

11
Course Elements
• Assignments (8+1): 18%
• Midterms (2): 20% each
• Final exam: 40%
• iClickers: 2% (1% participation + 1% correct answers)

• The grading scheme may change but should remain similar to this

• You must pass the final or a weighted average of the midterms and final
exam to pass the course

• No exemptions for iClickers under any circumstances (see note on syllabus)

12
Assignments
• There will be eight assignments (plus Assignment Zero)
• to be submitted on PrairieLearn (PL)

• You may work with a partner

• Maximum group size: 2
• Partnerships submit assignments jointly instead of separately
• You may discuss questions with other students
• see the Academic Conduct section of the syllabus
• Additional details in the course syllabus

13
 Assignments: Late Days

• Hand in assignments by the due dates on PrairieLearn

• You get four late days ☺

• allow some flexibility to manage unexpected issues
• you may use up to two late days on a given assignment
(unless otherwise specified)
• any exceptions will be specified in assignment instructions

14
Assignments: Late Days

• Additional late days will not be granted except under

truly exceptional circumstances
• Working with a partner does not give you more late
days
• If you’ve used up all your late days, you lose 20% per
day late
• Assignments will not be accepted more than two
days late

15
Missing Assignments/Readings/Midterm/Final
• Hopefully, late days will cover almost all the reasons for submitting late
assignments
• However, something more serious may occur 
• You may be eligible for exemptions (contact the course coordinator)

• If you miss (and are granted an exemption for):

• an assignment, your scores will be re-weighted to exclude it
• a midterm, the weight will be transferred to the final exam
• the final exam, you’ll have to make arrangements with your faculty
advising (Science, Arts, etc.)

16
How to Get Help
• Use Piazza for questions on course material
• people may already have posted similar questions
• please check before posting

• Go to office hours
• Initial times will be finalized next week

• Can schedule occasional appointments if you have conflicts with posted

office hours (or if other considerations apply)

17
Academic Conduct
• Carefully read and understand the Academic Conduct section in the syllabus
• If you are unsure of something, contact the instructor

• It is okay to discuss course material and assignments with your classmates;

learning from each other is good!

• However, all work that you submit must be your own

• If you use external sources (online, other students, etc.) in the assignments,
make sure you cite them
• whatever format you prefer, so long as we can easily find the source
based on the citation 18
Academic Conduct

For iClickers:

• You may collaborate fully with your neighbors/classmates

• You may not input someone else’s answers for them

19
Academic Conduct

• See the UBC documentation on what constitutes plagiarism

• Additional course policies are given in the syllabus on Canvas
• If you’re not sure whether the line is crossed, ask
• Ignorance of the rules will not be accepted as an excuse for breaking them

• All unjustified cases get reported to the Dean’s office

• Better to get a zero on an assignment than
• “academic misconduct” on your permanent transcript
• additional penalties up to expulsion

20
Course Logistics - Summary

• Course logistics and policies are described on Canvas and summarized in

these slides

• Make sure you carefully read and understand them

21
TIPS FOR SUCCESS IN CPSC 322
• Focus on understanding
• Read specified textbook sections before each class
• Actively participate in the lectures
• Spend time outside class reviewing and making sure you
understand the material
• Read assignment and exam questions carefully
• What’s the most likely interpretation, given the information
provided?
• Don’t procrastinate asking questions
• Course concepts often build on each other
• Review concepts from previous courses as needed
• CPSC 121, CPSC 221 22
Today’s Class: Learning Goals

• Explain what AI is

• Describe what an intelligent agent is

23
What is Intelligence?
"For instance, on the planet Earth, man had always
assumed that he was more intelligent than dolphins
because he had achieved so much—the wheel, New York,
wars and so on—whilst all the dolphins had ever done
was muck about in the water having a good time. But
conversely, the dolphins had always believed that they
were far more intelligent than man—for precisely the
same reasons."

Douglas Adams, The Hitchhiker's Guide to the Galaxy

24
What is Intelligence?
Let’s brainstorm together
- Take in stimuli and act (with a goal)
- Making decisions
- Using previous knowledge
- Applying new information to a problem
- Acting like humans!
- Solve problems
- Draw useful conclusions from new information
- Adopt to environment
- Learn
25
What is Artificial Intelligence?

Two definitions that have been proposed: Think Humanly Think Rationally
cognitive modelling “Laws of thought”
• Systems that think and act like humans Act Humanly Act Rationally
• Systems that think and act rationally Turing Test rational agent

26
Thinking and Acting like Humans

Model the cognitive functions of human beings

• Humans are our only example of intelligence:

we should use that example!

27
Thinking and Acting like Humans
Alan Turing (1912-1954)

I propose to consider the question,

“Can machines think?”

The Turing Test

• Don't try to come up with a list of characteristics that computers
must satisfy to be considered intelligent
• Instead, use an operational definition: consider it intelligent when
people can't tell a computer apart from other people
• Total Turing Test includes a video signal
28
Thinking and Acting like Humans

29
Thinking and Acting like Humans
Problems

• Humans often think/act in ways

that we don't consider intelligent
• Is acting just like a person what we really want?

• A detailed model of
how people's minds operate is not yet available

• Trickery or lying may be involved in evaluation

30
Turing Test: Sample Conversation
C: Tell me a sarcastic joke.
A: Count me out on this one. I am not good at sarcasm.
(ducking the question)

C: Add 34957 to 70764.

A: (Pause 30-45 seconds, then give answer) 105621.

31
Thinking and Acting Rationally
Rationality: an abstract “ideal” of intelligence,
rather than “whatever humans think/do”

• Ancient Greeks invented syllogisms:

argument structures that always yield
correct conclusions given correct premises
• This led to logic and probabilistic reasoning, which we'll
discuss in this course

• But is correct reasoning always enough?

• E.g., in some applications we may need some irrationality!
33
Thinking and Acting Rationally
This course will emphasize a view of AI as building agents: artifacts
that are able to think and act rationally in their environments
• Rationality is more cleanly defined than human behavior,
so it's a better design objective
• E.g., “intelligent” vacuum cleaner maximizes area cleaned, minimizes
noise and electricity consumption
• Agents that can answer queries, plan actions and solve complex
problems
• When you have a rational agent, you can always tweak it to
make it irrational!
34
Agents acting in an environment

Representation
and
Reasoning

35
What is an Agent?
More of these & more sophisticated
It has the following characteristics: => more intelligent

• It is situated in some environment

• does not have to be the real world---can be an abstracted electronic
environment
• It can make observations (perhaps imperfectly)
• It is able to act (provide an answer, buy a ticket)
• It has goals or preferences (possibly of its user)
• It may have prior knowledge or beliefs, and some way of
updating beliefs based on new experiences (to reason, to make
inferences)
36
What is an Agent?
Which of these things are agents?
Why or why not?
• A soccer-playing robot • It is situated in some environment
• A rock • It can make observations
• It is able to act
• Language translation software • It has goals or preferences
• A thermostat • It may have prior knowledge or
beliefs, and some way of updating
• A dog beliefs based on new experiences
• A car

37
Thinking and Acting Rationally
This course will emphasize a view of AI as building agents: artifacts
that are able to think and act rationally in their environments

• Act appropriately given goals and circumstances

• Flexible to changing environments and goals
• Learn from experience
• Make appropriate choices
given perceptual and computational limitations
• Gather information (if cost less than expected gain)
38
A Brief History of AI
Ada Lovelace (1815-1852)

39
A Brief History of AI

40
 More info: aaai.org/Magazine/ailandscape.php

41
In-class Activity

• Work in small groups searching the web to find an interesting

example of fielded (or experimental) intelligent agents
• Try to find something different from the usual suspects (Alexa, Siri,
Watson, ChatGPT, Copilot, Geminin, etc.)
• AAAI is the main AI association, so feel free to start there, but you
encounter plenty on a daily basis!

42
In-class Activity
Answer the following questions (and take notes):
1. What does the application do? (e.g,. control a spacecraft, perform
medical diagnoses, provide help for computer users, shop on eBay,
perform translation)
2. List some of the application’s: goals/preferences; observations that it
needs about the environment; types of actions that it performs
3. What AI technologies does the application use? (e.g,. belief networks,
Markov models, semantic networks, heuristic search, constraint
satisfaction, planning)
4. Why is it intelligent? Which aspects make it an intelligent system?
5. Is it an experimental system or a fielded system (i.e., used in a real
world setting)?
6. Is there evidence on how well the application performs?
43
Assignment Zero

• Available on PrairieLearn
• You may work in groups larger than 2 (for this assignment ONLY)
• You may not use late days, and late submissions will not be
accepted
• The good news: you already started it!

44