COMP30024 Artificial Intelligence
AIMA Slides © and ; 1
Copyright By PowCoder代写 加微信 powcoder
AI is Everywhere
Healthcare Customer Service Transportation
Manufacturing Smart HomesGaming
But AI has many risks and limitations,
both inherent in the technology, and how it is used
AIMA Slides © and ; 2
Our AI Team
♢ To contact lecturers:
♢ Lecturers: Prof.
♢ Head tutor:
AIMA Slides © and ; 3
♢ Research interests:
Machine Learning
Large-Scale Data Mining
Cyber Security
Telecommunications
♢ Industry research partners:
♢ Homepage:
https://findanexpert.unimelb.edu.au/profile/6335-christopher-leckie
AIMA Slides © and ; 4
General Information
♢ Text: Artificial Intelligence: A Modern Approach,
& , 4th Edition, Pearson, 2021
(earlier editions are fine)
♢ Lecture slides available on LMS, lectures recorded on Lecture Capture
♢ Subject LMS discussion board for student discussion
♢ Workshops (aka tutorials) are one hour and start week 2
AIMA Slides © and ; 5
Prerequisites
♢ Subjects:
COMP20003 Algorithms and Data Structures or
COMP20007 Design of Algorithms
Data structures & algorithms coding in Python
(This subject does not include programming language tuition)
Familiarity with formal mathematical notation
Basic understanding of differential calculus and probability theory helpful
but not essential
AIMA Slides © and ; 6
Assessment
♢ Assessment: 70% exam, 30% project (programming project in Python)
♢ Requirements: 15/30 project hurdle, 35/70 exam hurdle, 50/100 overall
♢ Project: a single project in 2 parts
Part A due 30th March. Part B due 11th May.
(to be confirmed in project specification on subject LMS site)
♢ Project is to implement a game playing agent in Python
♢ You will work on the project in a team of two people
♢ We will discuss the project in more detail next lecture,
and over the coming weeks
AIMA Slides © and ; 7
Who and Where
♢ Lectures:
Wednesdays 2.15–3.15 pm
Thursdays 10–11 am
♢ Tutorials: (per your registration)
♢ Feedback:
During/after lecture
Assignment feedback
Discussion board
Consultation sessions (to be announced)
General inquiries:
AIMA Slides © and ; 8
Topic AIMA 2nd ed 3rd ed 4th ed
What is AI? (wk1) Ch1 Ch1 Ch1
Intelligent Agents (wk1) Ch2 Ch2 Ch2
Solving Problems by Searching (wk2) Ch3 Ch3 Ch3
Informed Search Methods (wk3) Ch4 Ch3 Ch3
Adversarial Search (wk4) Ch6 Ch5 Ch6
Learning in Games (wk5) notes notes notes
Feedback Quiz (wk6) – – –
Advanced Topic (wk6) – – –
Constraint Satisfaction (wk7) Ch5 Ch7 Ch5
Making Collective Decisions (wk8) Ch17 Ch17.6 Ch17.4
Uncertainty (wk9) Ch13 Ch13 Ch12
Probabilistic Reasoning (wk10) Ch14 Ch14 Ch13
Robotics (wk11) Ch25 Ch25 Ch26
Revision and Tournament (wk12) – – –
AIMA Slides © and ; 9
Week 1: What is AI?
AIMA Slides © and ; Chapter 1 10
♢ Defining AI
♢ Tests for intelligence
♢ State of the art
AIMA Slides © and ; Chapter 1 11
Types of Intelligence
♢ The big question: How does the mind arise from the brain?
♢ How many different types of “intelligent” behaviour can you think of?
AIMA Slides © and ; Chapter 1 12
Four approaches to defining AI
♢ Thinking like a human
♢ Thinking rationally
♢ Acting like a human
♢ Acting rationally
AIMA Slides © and ; Chapter 1 13
Thinking like a human
Cognitive modelling: figure out how we think by introspection
or experimentation
Self-awareness is important: “I think therefore I am”
Humans feel emotions and apparently don’t always think (or act) rationally
AIMA Slides © and ; Chapter 1 14
Thinking rationally
The laws of thought:
eg “Socrates is a man. All men are mortal.
Therefore Socrates is mortal”
Codifying rational thinking started with Aristotle (at least in the West)
The study of logic has greatly influenced AI
AIMA Slides © and ; Chapter 1 15
Aspects of Intelligence
Abstract thinking and problem solving
Learning and memory
Language, communication
Intuition and creativity
Consciousness
Surviving in a complex world
Adapting to new situations
AIMA Slides © and ; Chapter 1 16
Test for Intelligence: The Turing test
Proposed by in 1950
A human interrogates/converses with the computer via a teletype
The aim is for the computer to imitate a human well enough to fool people
Turing thought a computer would pass this test by the end of the century
The Loebner Prize (Turing test) competition is held each year
The “total Turing test” allows physical objects to be passed to the machines
as well as characters via the teletype
AIMA Slides © and ; Chapter 1 17
Acting humanly: The Turing test
Turing (1950) “Computing machinery and intelligence”:
♢ “Can machines think?” −→ “Can machines behave intelligently?”
♢ Operational test for intelligent behavior: the Imitation Game
INTERROGATOR
♢ Predicted that by 2000, a machine might have a 30% chance of
fooling a lay person for 5 minutes
♢ Anticipated all major arguments against AI in following 50 years
♢ Suggested major components of AI: knowledge, reasoning, language
understanding, learning
Problem: Turing test is not reproducible, constructive, or
amenable to mathematical analysis
AIMA Slides © and ; Chapter 1 18
Eliza Session
The earliest attempt was a system called Eliza (1966).
Eliza: What brought you here to see me today?
Visitor: Oh, nothing much. I’m feeling a bit tired, that’s all.
Eliza: Why do you think you’re feeling a bit tired?
Visitor: Well, I’ve been traveling a lot, and away from home.
Eliza: Tell me more about your family
AIMA Slides © and ; Chapter 1 19
Eliza Session
Visitor: The trouble is, my mother’s ill.
Eliza: How long has she been ill?
Visitor: The trouble is, my mother’s Irish.
Eliza: How long has she been Irish?
Visitor: The trouble is, my mother’s poodle.
Eliza: How long has she been poodle?
AIMA Slides © and ; Chapter 1 20
Acting rationally
The rational agent: perform actions which will
(most likely) achieve one’s goals
Knowledge may not be perfect — we need to go beyond
strict rational thought in general
The rational agent view is the basis of
“Artificial Intelligence: A Modern Approach”
AIMA Slides © and ; Chapter 1 21
State of the art
Which of the following can be done at present?
♢ Play a decent game of table tennis
♢ Drive along a curving mountain road
♢ Drive down Brunswick St on a Saturday night
♢ Play a decent game of bridge
♢ Discover and prove a new mathematical theorem
♢ Write an intentionally funny story
♢ Give competent legal advice in a specialized area of law
♢ Translate spoken English into spoken Japanese in real time
AIMA Slides © and ; Chapter 1 22
State of the Art
Machine translation: try Google Translator
(https://translate.google.com)
Conversational agents: Apple’s Siri, IBM’s Watson for question answering
Robotic vehicles: Google self-driving car autonomous vehicle that can drive
safely though traffic
(https://www.google.com/selfdrivingcar/)
Versatile robots: 2015 DARPA Robotics Challenge – mobile robot that can
walk over rubble and operate power tools
Human action recognition: Microsoft Kinect
AIMA Slides © and ; Chapter 1 23
https://translate.google.com
https://www.google.com/selfdrivingcar/
♢ Defining AI
– Explain different approaches to defining AI
♢ Tests for intelligence
– Describe the operation of the Turing test
♢ State of the art
– Characterise the difficulty of different common tasks
What to do now:
– Find a project partner
– Brush up your Python
– Tutorials start in Week 2
AIMA Slides © and ; Chapter 1 24
Week 1: Intelligent Agents
AIMA Slides © and ; Chapter 2 25
♢ Agent model
♢ Agent types
♢ Environment types
AIMA Slides © and ; Chapter 2 26
Intelligent agents
♢ chess/backgammon
♢ refinery controller
♢ medical diagnosis
♢ flight reservations
♢ walking on two legs
♢ taxi driver
♢ vacuum cleaning
♢ robocup soccer
AIMA Slides © and ; Chapter 2 27
The Agent Model
♢ Percepts/observations of the environment, made by sensors
♢ Actions which may affect the environment, made by actuators
♢ Environment in which the agent exists
♢ Performance measure of the desirability of environment states
AIMA Slides © and ; Chapter 2 28
Example: automated taxi
Percepts: video, accelerometers, gauges, engine sensors, keyboard, GPS,
Actions: steer, accelerate, brake, horn, speak/display, . . .
Environment: city streets, freeways, traffic, pedestrians, weather, cus-
tomers, . . .
Performance measure: safety, reach destination, maximize profits, obey
laws, passenger comfort, . . .
AIMA Slides © and ; Chapter 2 29
Agents as functions
Agents can be evaluated empirically, sometimes analysed mathematically
Agent is a function from percept sequences to actions
Ideal rational agent would pick actions which are expected to maximise
its performance measure (based on the percept sequence and its built-in
knowledge)
Rational ̸= omniscient
Rational ̸= clairvoyant
Rational ̸= successful
AIMA Slides © and ; Chapter 2 30
Agent types
♢ simple reflex agents
♢ model-based reflex agents
♢ goal-based agents
♢ utility-based agents
AIMA Slides © and ; Chapter 2 31
Simple reflex agents
AIMA Slides © and ; Chapter 2 32
Model-based reflex agents
AIMA Slides © and ; Chapter 2 33
Goal-based agents
AIMA Slides © and ; Chapter 2 34
Utility-based agents
AIMA Slides © and ; Chapter 2 35
Environment types
Environments may or may not be
♢ Observable: percept contains all relevant information about the world
♢ Deterministic: current state of the world uniquely determines the next
♢ Episodic: only the current (or recent) percept is relevant,
and short-term actions do not have long-term consequences
♢ Static: environment doesn’t change while the agent is deliberating
♢ Discrete: finite number of possible percepts/actions
AIMA Slides © and ; Chapter 2 36
Environment types
Solitaire Backgammon Internet shopping Taxi
Observable
Deterministic
The environment type largely determines the agent design
The real world is (of course) partially-observable, stochastic, sequential, dy-
namic, continuous
AIMA Slides © and ; Chapter 2 37
Environment types
Solitaire Backgammon Internet shopping Taxi
Observable Yes Yes No No
Deterministic Yes No Partly No
Episodic No No No No
Static Yes Yes Semi No
Discrete Yes Yes Yes No
The environment type largely determines the agent design
The real world is (of course) partially-observable, stochastic, sequential, dy-
namic, continuous
AIMA Slides © and ; Chapter 2 38
♢ Agent model
– characterise requirements for an agent in terms of its percepts, actions,
environment and performance measure
♢ Agent types
– choose and justify choice of agent type for a given problem
♢ Environment types
– characterise the environment for a given problem
AIMA Slides © and ; Chapter 2 39
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com