CSE 3521: �Introduction to Artificial Intelligence�

[These slides are partially adapted from the UC Berkeley. CS188 Intro to AI at UC Berkeley]

Course information

• Course website:

https://sites.google.com/view/osu-cse-3521-sp24-chao/home

(for course information, weekly schedule, and reading update)

​

• Instructor: Dr. Wei-Lun Chao (chao.209@osu.edu)
• Assistant professor in CSE (PhD: USC; Postdoc: Cornell)
• Office: DL 587

​

• TA: TBD

​

​

​

A bit about my research in ML

Machine learning and its applications to

• Autonomous driving
• Computer vision
• Natural language processing
• Health care
• Imageomics

​

​

​

​

3

A bit about my research in ML

Learning with “imperfect” data sources

• Limited data
• Imbalanced data
• Inaccessible data
• Domain shifts

​

​

4

Course information

• Lecture time: Wednesday and Friday, 2:20 PM - 3:40 PM

​

• Office hours: Monday and Thursday 5:30 PM - 6:30 PM
• No office hours the first week

​

• TA Office hours: TBA
• No office hours the first week

​

​

Course information

• Carmen/GitHub:
• For announcement, posting course materials (slides), and homework submission

​

• Carmen quizzes:
• For quizzes

​

• Carmen/Piazza:
• For discussion. More information to be announced.

​

• Detailed syllabus (pdf):
• can be found on Carmen and the course website

​

6

Communications

• Schedule and reading will be updated on the website
• Announcements will be made through Carmen
• Discussions and questions must be posted in Piazza
• Please only use email to contact me or the TA for urgent or personal issues. Please include the tag "[OSU-CSE-3521]" in the subject line.
• More details: See website, Carmen, and the syllabus

​

7

Questions?

Pre-requisites & what to expect?

• Pre-requisites
• CSE 2331 (Foundations 2) or 5331
• Linear algebra: Math 2568, 2174, 4568, or 5520H
• Statistics, probability: Stat 3201 or 3450 or 3460 or 3470 or 4201 or Math 4530 or 5530H
• Suggested: MATH 3345 (Foundations of Higher Math)
• reasonable degree of mathematical sophistication
• knowledgeable of basic algorithm design techniques and data structures
• Extensive math and programming related Homework
• Linear algebra, probability, and (multivariate) calculus
• Programming: Python 3
• AI algorithms often difficult to debug
• We strongly recommend that you start early.

Grading and homework

 Grading Policy (Tentative)

• Homework & Labs – 40%
• Quizzes & participation – 10%
• Midterm – 25%
• Final – 25% (cumulative)
• I may redistribute the midterm and final exams (and percentage) to three exams

​

Guidelines

•  Expect 4-5 homework assignments (including problem and programming sets)
• Solutions involve derivations or proofs. Grading is based on correctness and clarity. Be concise and show your reasoning in a clear and precise way.
• Homework completion and submissions are individual, but feel free to discuss. You must strictly follow the submission instructions.
• NOT ALLOWED: ask or search solutions
• No late days are accepted.

​

​

Tentative schedule

Linear algebra quizzes (Carmen)

• Due: 1/24
• 8 of them (AI_linear_algebra_n)
• Each is 0.5 points
• Multiple attempts; the LAST is counted
• You may do each quiz first. If you find it difficult, you may review the corresponding slide deck in the Linear Algebra Review module.

​

Other quizzes (Carmen)

• Due will be on Wednesday
• The quiz will be released on the Friday before
• There will be at most 12 of them
• Each is 0.5 point (within 10 mins of work)

Due is all at 23:59 ET

Tentative schedule

Homework

• Dates: TBA
• You will have two weeks to complete each homework

​

Exams

• Midterm date(s): TBA
• Final exam: 4/24

Policy

Academic integrity

• Plagiarism and other unacceptable violations
• Zero tolerance
• Please study the related sections in the syllabus (pdf) on academic integrity.
• Please read OAA’s message on large language models: https://oaa.osu.edu/artificial-intelligence-and-academic-integrity

​

(Re-)grading

• Only factual errors will be corrected.
• Request: one week within the release of your homework and exam grade
• Format: TBA

​

Important for this week

• Register. If you are on the waitlist, you might or might not get in depending on how many empty seats or how many students drop.
• Register for the class on piazza (see Carmen for the link) --- our main platform for discussion and communication
• Math review/self-diagnostic:
• Do the linear algebra quizzes and review linear algebra (via the slide decks)
• Check the suggested materials on the website
• Important to check your preparedness for the course
• Python: check suggested tutorials on the website
• Decision: stay or drop
• Office hours: start next week

​

14

Important dates

• Potential travel: 2/7, 2/16, 2/23
• We will use Zoom

15

Questions?

Textbook

​

• Not required, but for students who want to read more, we recommend

​

​

​

​

​

​

​

​

​

​

​

​

​

​

• Warning: Not course textbooks, so our notation/presentation does not necessarily follow the book.
• See Carmen for PDF links.

​

​

​

Russell & Norvig,

AI: A Modern Approach, 3^rd Ed.

Bishop,

Pattern Recognition and Machine Learning

Other great textbooks

Machine Learning:

A Probabilistic Perspective

Deep Learning

Understanding Machine Learning

Introduction to Machine Learning

Other excellent resources

• Stanford CS 188: Introduction to Artificial Intelligence
• https://inst.eecs.berkeley.edu/~cs188/su21/

​

• The Matrix Cookbook

​

​

How to do well? How to learn AI well?

• Lecture and lecture slides for basics
• Describe basic concepts, tools
• Describe algorithms and their development with intuition and rigor

​

• Textbook reading for extension
• Homework for practice, generalization, and implementation
• Discussion (Carmen/Piazza, office hours) for further understanding

​

• Overall: Develop skills on grasping abstract concepts and thinking critically to solve problems with AI techniques

Questions?

Today

• Introduction
• What is artificial intelligence?
• What can AI do?
• What is this course?

​

• Agent design

​

​

Sci-Fi AI?

Sci-Fi AI?

Sci-Fi AI?

Bicentennial Man (1999)

Some definitions of AI

• “The scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines”

– American Association of Artificial Intelligence (AAAI)

​

• “Artificial Intelligence is the branch of computer science that is concerned with the automation of intelligent behavior”

– Luger and Stubblefield

​

• “AI strives to understand and build intelligent entities (also helps us to learn more about ourselves)”

– Russell and Norvig

​

What is AI?

The science of making machines that:

Think like people

Act like people

Think rationally

Act rationally

What is AI?

How can we test it?

The Turing Test

• Ingredients:
• Human Judge, unknown Entity
• 2 computer terminals in different room��
• Recipe:
• Have human Judge sit at one computer
• Judge converses with Entity via chat window for 5 minutes
• Judge decides if Entity is human or computer

​

 Which is which?

Left hand side

• Judge: Hi what’s your name?
• Entity: I don’t know
• Judge: My name’s Jane. I live in London. Where do you live?
• Entity: I live in London as well
• Judge: Do you like living in London?
• Entity: Yes, I like it because there are a lot of things to do, and it is the capital city of England
• Judge: What’s my name?  
• Entity: sorry?  
• Judge: What’s my name?
• Entity: Jane
• Judge: And what’s your name?
• Entity: I don’t know

​

Right hand side

• Judge: What color is the carpet in your room
• Entity: I like pink; what do you like?
• Judge: I like pink. My name is John. What’s your name?
• Entity: Red. Hello John. Its nice to meet such a fine person as yourself.
• Judge: Red is my favorite color. What’s yours?
• Entity: My favorite color is red.
• Judge: You use American spelling. Are you in the USA?
• Entity: But you are not even American. Just remember atheism is only a belief system. And it too can be forced on people who don’t agree.
• Judge: How do you like your eggs – ever easy or sunny side up?
• Entity: How I wonder if I like my eggs-over easy or sunny side up? This is so explainable. That list makes me feel unsure John.

​

Example taken from “Turing’s Imitation Game,” by Warwick and Shah (2016)

How to do well in the Turing Test?

• Chatting “like a human” involves:
• Generating coherent language
• Responding appropriately to unexpected inputs
• …

​

What is not shown?

• The Turing Test does not show
• Understanding or thinking
• Ability to learn
• Interaction with an unconstrained world
• Processing sensory input
• Having knowledge
• Much of anything useful, really

​

Act rationally; rational decisions

• We’ll use the term rational in a very specific, technical way:
• Rational: maximally achieving pre-defined goals
• Rationality only concerns what decisions are made (not the thought process behind them)
• Goals are expressed in terms of the utility of outcomes
• Being rational means maximizing your expected utility
• Rational behavior = doing the right thing, does not necessarily involve thinking

​

​

Act rationally; rational decisions

• We’ll use the term rational in a very specific, technical way:
• Rational: maximally achieving pre-defined goals
• Rationality only concerns what decisions are made (not the thought process behind them)
• Goals are expressed in terms of the utility of outcomes
• Being rational means maximizing your expected utility
• Rational behavior = doing the right thing, does not necessarily involve thinking

​

• Example:
• Goal: do well in the CSE 3521 course
• Utility: final grade
• Being rational: review math materials and do the Linear Algebra quizzes!

​

​

​

A (** Short **) history of AI

• 1940-1950: Early days
• 1943: McCulloch & Pitts: Boolean circuit model of brain
• 1950: Turing's “Computing Machinery and Intelligence”

​

• 1950—70: Excitement: Look, Ma, no hands!
• 1950s: Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine
• 1956: Dartmouth meeting: the term “Artificial Intelligence” adopted
• 1965: Robinson's complete algorithm for logical reasoning

​

• 1970—90: Knowledge-based approaches
• 1969—79: Early development of knowledge-based systems
• 1980—88: Expert systems industry booms
• 1988—93: Expert systems industry busts: “AI Winter”

​

• 1990—: Statistical approaches
• Resurgence of probability, focus on uncertainty
• General increase in technical depth
• Agents and learning systems… “AI Spring”?

​

• 2000—: Where are we now? (Machine learning, neural networks, deep learning, large language models)

What can AI do? (2021 version)

Practice: Which of the following can be done at present?

​

• Play a decent game of table tennis?
• Play a decent game of Jeopardy/Go/Atari/Star raft?
• Drive safely along a curving mountain road (w/o other traffic agents)?
• Drive safely along High Street?
• Buy a week's worth of groceries on the web?
• Buy a week's worth of groceries at Worthington Farmers Market?
• Discover and prove a new mathematical theorem?
• Converse successfully with another person for an hour?
• Perform a surgical operation?
• Put away the dishes and fold the laundry?
• Translate spoken Chinese into spoken English in real time?
• Write an intentionally funny story?

Questions?

Important research areas related to AI

• Speech processing
• Natural language processing
• Computer vision
• Robotics
• Logic
• Game playing
• Decision making
• Autonomous driving
• ……

​

​

Speech processing & Natural language processing

• Speech technologies (e.g., Siri, Alexa)
• Automatic speech recognition (ASR)
• Text-to-speech synthesis (TTS)
• Dialog systems

​

• Language processing technologies
• Question answering
• Machine translation

​

​

​

​

​

​

• Web search
• Text classification, spam filtering, etc…
• Large language models (LLM)

Computer vision

[Source: Detectron2]

• Object and face recognition
• Scene segmentation
• Image classification

[Source: Graham Murdoch/Popular Science]

Robotics

• Robotics:
• Part mechanical engineering
• Part AI
• Reality much harder than simulations!

​

• Technologies:
• Vehicles
• Rescue
• Soccer!
• Lots of automation …

​

• In this class:
• We ignore mechanical aspects
• Methods for planning (and/or control)

[Images from UC Berkeley, Boston Dynamics, RoboCup, Google]

Logic

• Logical systems:
• Theorem provers
• NASA fault diagnosis
• Question answering

​

• Methods:
• Deduction systems
• Constraint satisfaction
• Satisfiability solvers (huge advances!)

[ Image from Bart Selman ]

Game playing

• Classic Moment: May, '97: Deep Blue vs. Kasparov
• First match won against chess world champion
• “Intelligent creative” play
• 200 million board positions per second
• Humans understood 99.9 of Deep Blue's moves
• Can do about the same now with a PC cluster

​

• Open question:
• How does human cognition deal with the

search space explosion of chess?

• Or: how can humans compete with computers at all?

​

• 1996: Kasparov beats Deep Blue

“I could feel --- I could smell --- a new kind of intelligence across the table.”

​

• 1997: Deep Blue beats Kasparov

“Deep Blue hasn't proven anything.”

​

• Huge game-playing advances recently, e.g., in Go, Atari, and Computer games!

​

[ Text from Bart Selman, image from IBM’s Deep Blue pages, Google DeepMind]

Decision making

• Applied AI involves many kinds of automation
• Scheduling, e.g., airline routing, military
• Route planning, e.g., Google maps
• Medical diagnosis
• Web search engines
• Spam classifiers
• Automated help desks
• Fraud detection
• Product recommendations
• … Lots more!

Autonomous driving

Radar

Sonar

Camera

Others

LiDAR

Something new

Something new

This course

• Search: How do I (efficiently) find a solution?
• Logic and Knowledge: How do I determine what is/isn’t known?
• Decision Policies: How do I choose the best next action?
• Probability: How do I handle dependency and non-determinism?  
• Machine Learning: How do I learn from data and/or experience?
• Philosophy and Ethics: How do I determine what is intelligent? And how do I know that what I’m doing is good?
• Something new: Recent advancements in large language/foundation models

​

This course (topics)

• AI agent design
• Search
• Symbolic AI & Logical Inference
• Data-to-features and dimensionality reduction
• General parameter estimation techniques
• Probability basics and probabilistic methods
• Unsupervised learning
• Supervised learning
• Neural networks and deep learning
• Reinforcement learning basics
• Ethics and philosophy of AI

CSE 3521: Agent Design

[Many slides are adapted from the UC Berkeley. CS188 Intro to AI at UC Berkeley and previous CSE 3521 course at OSU.]

What is AI?

The science of making machines that:

Think like people

Act like people

Think rationally

Act rationally

The Fundamental question for this lecture

(and really this whole AI field!):

​

​

​

​

​

​

How do you turn a real-world

​

problem into an AI solution?

AI – agents and environments

• Much (though not all) of AI is concerned with agents operating in environments.
• Environment – the problem setting
• Agent – an entity that perceives its environment through sensors and acts upon that environment through effectors (actuators)

​

​

​

AI – agents and environments

Environment

Agent

perception

action

Sensors: eyes, ears, etc.

Effectors: hands, legs, mouth, etc.

Humans

Sensors: cameras, 3D sensors, etc.

Effectors: various motors, robot arms, etc.

Robots

Cross walks

AI – agents and environments

Environment

Agent

perception

action

Sensors: eyes, ears, etc.

Effectors: hands, legs, mouth, etc.

Humans

Sensors: cameras, 3D sensors, etc.

Effectors: various motors, robot arms, etc.

Robots

Cross walks

• Percept: Agent’s perceptual inputs at any given instant
• Percept sequence: Complete history of everything agent has perceived
• Agent’s choice of action (e.g., walk forward for a step, push the bottom) can depend on entire percept sequence

Fleshing it out

• Performance – measuring the agent’s success

​

​

• Environment – what populates the problem’s world?

​

​

• Actuators – what can the agent act with?

​

​

• Sensors – how can the agent perceive the world?

​

Peas in autonomous taxi

• Performance – Safe, fast, legal, and comfortable trip; maximize profits

​

• Environment – Roads, other traffic agents (e.g., pedestrians), customers

​

• Actuators – Steering, accelerator, brake, signals, horn, display

​

• Sensors – Cameras, sonar, LiDAR, radar, speedometer, GPS, odometer, � accelerometer, engine sensors, microphone/keyboard

​

Peas: Other examples

In class exercise

• Give a ‘PEAS’ description of the task environment for the following vacuum-cleaner world with four locations.

​

In class exercise

• Give a ‘PEAS’ description of the task environment for the following vacuum-cleaner world with four locations.

​

• Performance – cleanness, efficiency, distance traveled

​

• Environment – room with 4 squares

​

• Actuators – wheels, brushes, vacuum extractor

​

• Sensors – dirt detection

​

Summary

• Introduction to AI
• Act like humans vs. act rationally
• AI applications
• Agent design (part 1)
• Agents and environments
• PEAS: performances, environments, actuators, sensors.

​

​

​