Ar Arti tifici ficial al In Inte tell llig igenc ence e (A - - PowerPoint PPT Presentation

▶
ar arti tifici ficial al in inte tell llig igenc ence e a
SMART_READER_LITE
LIVE PREVIEW

Ar Arti tifici ficial al In Inte tell llig igenc ence e (A - - PowerPoint PPT Presentation

Dec 13, 2023 135 likes •387 views

In Intr trod oduc uctio tion n to to Ar Arti tifici ficial al In Inte tell llig igenc ence e (A (AI) I) Co Computer ter Sc Science ce cpsc3 c322, 22, Lectur ture e 1 January, ary, 4, 2010 CPSC 322, Lecture 1 Slide 1

slide-1
SLIDE 1

CPSC 322, Lecture 1 Slide 1

In Intr trod

  • duc

uctio tion n to to Ar Arti tifici ficial al In Inte tell llig igenc ence e (A (AI) I)

Co Computer ter Sc Science ce cpsc3 c322, 22, Lectur ture e 1

January, ary, 4, 2010

slide-2
SLIDE 2

CPSC 322, Lecture 1 Slide 2

Pe People

  • ple

Inst stru ruct ctor

  • r
  • Giuse

sepp ppe e Ca Carenini ( carenini@cs.ubc.ca; office CICSR 129)

Te Teachin hing g As Assista stants nts

  • Ha

Hammad ad Ali Ali hammada@cs.ubc.ca

  • Ke

Kenneth eth Al Alton kalton@cs.ubc.ca (will be starting Jan 18)

  • Scott

tt He Helmer shelmer@cs.ubc.ca

  • Sunjeet

et Singh sstatla@cs.ubc.ca

slide-3
SLIDE 3

CPSC 322, Lecture 1 Slide 3

Course urse Essential entials(1) s(1)

  • Course

se web-pag ages es:

www.cs.ubc.ca/~carenini/TEACHING/CPSC322-10/index.html WebSearch: Giuseppe Carenini

  • This is where most information about the course will be

posted, most handouts (e.g., slides) will be distributed, etc.

  • CHECK IT OFTEN!
  • Lectur

tures es:

  • Cover basic notions and concepts known to be hard
  • I will try to post the slides in advance (by noon).
  • After class, I will post the same slides inked with the notes I

have added in class.

  • Each lecture will end with a set of learning goals:

Student can….

slide-4
SLIDE 4

CPSC 322, Lecture 1 Slide 4

Course urse Essential entials(2) s(2)

  • Te

Textbo tbook

  • k: Artificial Intelligence, 2nd Edition, by Poole,
  • Mackworth. Under development (here at UBC), but almost

domne.

  • It’s free!
  • It’s available electronically

http://people.cs.ubc.ca/~poole/aibook/

  • We will cover at least Chapters: 1, 3, 4, 5, 6, 8, 9
  • PDF Available on WebCT
slide-5
SLIDE 5

CPSC 322, Lecture 1 Slide 5

Course urse Essential entials(3) s(3)

  • WebCT:

T: used for textbook, discussion board

  • Use the discussion board for questions about

assignments, material covered in lecture, etc. That way

  • thers can learn from your questions and comments!
  • Use email for private questions (e.g., grade inquiries or

health problems).

  • AI

AIspac ace e : online tools for learning Artificial Intelligence http://aispace.org/

  • Also under development

here at UBC!

slide-6
SLIDE 6

CPSC 322, Lecture 1 Slide 6

Course urse Elements ments

  • Pr

Practic tice e Ex Exercis ises es: : 0%

  • As

Assign gnmen ents ts: 20%

  • Midter

erm: m: 30%

  • Fi

Final: l: 50%

If f your final grade is >= 20% higher than your midterm erm grade:

  • Assignments: 20%
  • Midterm: 15%
  • Final: 65%
slide-7
SLIDE 7

CPSC 322, Lecture 1 Slide 7

Assignments ignments

  • Th

There e wi will be five e assig ignm nment ents s in total al

  • Counting “assignment zero”, which you’ll get today
  • They will not necessarily be weighted equally
  • Group

p work

  • code questions:

you can work with a partner always hand in your ur own piece ce of code (stating who your partner was)

  • written questions:

you may discuss questions with other students you may not look at or copy each other's written work you'll be asked to sign an honour code saying you've followed these rules

slide-8
SLIDE 8

CPSC 322, Lecture 1 Slide 8

Assignments: ignments: Late te Days

  • Hand in by 3PM

PM on due day (in class or electronically)

  • Yo

You get four late days 

  • to allow you the flexibility to manage unexpected issues
  • additional late days will not be granted except under

truly exceptional circumstances

  • A d

A day is define ned as: all or part of a 24-hour block of time

beginning at 3 PM on the day an assignment is due

  • Applicable to assignments 1- 4 not

not applic icab able le to assig ignm nmen ent t 0, midterm, rm, final!

  • if you've used up all your late days, you lose 20%

per day

slide-9
SLIDE 9

CPSC 322, Lecture 1 Slide 9

Missing sing Assignm ignments ents / M / Midterm term / Fi / Final al

Hopeful fully ly late days will cover almost all the reasons you'll be late in submitting assignments.

  • However, something more serious like an extended illness

may occur 

  • Fo

For all such h cases es: : you'll need to provide a note from your

doctor, psychiatrist, academic advisor, etc.

  • If you miss:
  • an assignment

ment, , your score will be reweighted to exclude that

assignment

  • the midterm

rm, , those grades will be shifted to the final. (Thus, your

total grade = 80% final, 20% assignments)

  • the final,

, you'll have to write a make-up final as soon as possible.

slide-10
SLIDE 10

CPSC 322, Lecture 1 Slide 10

How w to to Ge Get t Help? p?

  • Use the course discussi

sion

  • n board on WebCT for questions
  • n course material (so keep reading from it)
  • Go to office hours (newsgroup is NOT a good substitute

for this) – times will be finalized next week

  • Giuse

sepp ppe: e: TBA (CI CICSR CSR #129)

  • Ha

Hammad ad TBA (learni rning g Ce Center) r)

  • Ken :

TBA (learni rning g Ce Center) r)

  • Scott

tt: : TBA (learni rning g Ce Center) r)

  • Sunjeet

et: : TBA (learni rning g Ce Center) r) Can schedule by appointment if you can document a conflict with the official office hours

slide-11
SLIDE 11

CPSC 322, Lecture 1 Slide 11

Get etting ting Hel elp p fr from

  • m Oth

ther er St Stud uden ents ts? ? (Pla lagia giarism rism)

  • It

t is OK OK to talk wi with your classmat mates es about assignments; ments; learning ng from m each other r is good

  • Bu

But you must:

  • Not copy from others (with or without the consent of the

authors)

  • Write/present your work completely on your own (code

questions exception)

  • See UB

UBC o C offi fici cial l regulati ation

  • ns on what constitutes

plagiarism (pointer in course Web-page)

  • Ignorance of the rules will not be a sufficient excuse for

breaking them

slide-12
SLIDE 12

CPSC 322, Lecture 1 Slide 12

Get etting ting Hel elp p fr from

  • m Oth

ther er Stu tude dent nts? ? (Pl Plag agiarism iarism)

When you are in do doubt wh whether er the line is crossed sed:

  • Talk to me or the TA’s

Any unjustified cases will be severely ely dealt wi with by the Dean’s Off ffice ice (that’s the official procedure)

  • My advice: better to skip an assignment than to have

“academic misconduct” recorded on your transcript and additional penalties as serious as expulsion from the university!

slide-13
SLIDE 13

CPSC 322, Lecture 1 Slide 13

To To Summarize arize

  • All the course logistics are described in the course

Webpage

www.cs.ubc.ca/~carenini/TEACHING/CPSC322-10/index.html

WebSearch: Giuseppe Carenini (And summarized in these slides)

  • Make sure you carefully read and understand them!
slide-14
SLIDE 14

CPSC 322, Lecture 1 Slide 14

What t is In Inte telligence? lligence?

slide-15
SLIDE 15

CPSC 322, Lecture 1 Slide 15

Wh What t is s Arti tificial ficial In Intel telligence? ligence?

Tw Two definitio itions ns that have been propose sed:

  • Systems that think

nk and act act like humans

  • Systems that think

nk and act act ration

  • nall

ally

slide-16
SLIDE 16

CPSC 322, Lecture 1 Slide 16

Th Thinking inking and Ac Acti ting ng Humanly anly

Model l the cogniti itive ve funct ction

  • ns

s of human beings gs

  • Humans are our only example of intelligence: we

should use that example! Pr Problem ems: s:

  • But... humans often think/act in ways that we

don't consider intelligent (why?)

  • And... detailed model of how people's minds
  • perate not yet available
slide-17
SLIDE 17

CPSC 322, Lecture 1 Slide 17

Th Thinki inking ng Rati tionally

  • nally

Ration

  • nal

ality ity: 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 probabili

ilist stic c reasoning ing which we'll discuss in this course

  • But correct sound reasoning is not always enough

“to survive” “to be useful”…

slide-18
SLIDE 18

CPSC 322, Lecture 1 Slide 18

Acti ting ng (&thi thinking) nking) Rati tionally

  • nally

This course will emphasize a view of AI as building agents nts: artifacts that are able to think and act rationally in their environments Rationality is more cleanl nly y defined ed than human behavior, so it's a better design objective

(Eg: “intelligent” vacuum cleaner: maximize area cleaned, minimize noise and electricity consumption)

Agents that can answer queries, plan actions and solve complex problems And when you have a rational agent you can always tweak it to make it irrational!

slide-19
SLIDE 19

CPSC 322, Lecture 1 Slide 19

Wh Why do we need ed intel telligent ligent agent ents? s?

slide-20
SLIDE 20

CPSC 322, Lecture 2 Slide 20

Agents ents acti ting ng in an environ ironment ment

Representation & Reasoning

slide-21
SLIDE 21

CPSC 322, Lecture 1 Slide 21

Wh What t is an agent? nt?

It has the following characteristics:

  • It is situated in some enviro

ronm nmen ent

  • does not have to be the real world---can be an abstracted

electronic environment

  • It can make observ

rvati ation

  • ns

s (perhaps imperfectly)

  • It is able to act

act (provide an answer, buy a ticket)

  • It has goals or prefere

renc nces es (possibly of its user)

  • It may have prior knowl

wled edge ge or beliefs fs, and some way of updatin ting beliefs efs based on new experiences (to reason, to make inferences)

slide-22
SLIDE 22

CPSC 322, Lecture 1 Slide 22

Fo For Fr Fri: : Assignment ignment 0

  • Your first assignment asks you to find two example

les s of field lded ed or experime imenta ntal l AI AI agents ts, and to explain some high-level details about how they work.

  • The assignment is available from the course

se we web page ge

  • submit

it electro troni nica cally lly and you can't 't use late days

Fo For We Wed: : Read ad Chp 1 TO TODO O fo for th this week

slide-23
SLIDE 23

CPSC 322, Lecture 1 Slide 23

Examples mples

Which of these things is an agent agent, and why or why not?

  • A soccer-playing robot?
  • A rock?
  • Machine Translator?
  • A thermostat?
  • A dog?
  • A car?

Which of these things is an intell llige igent nt agent, and why or why not?

slide-24
SLIDE 24

CPSC 322, Lecture 1 Slide 24

Acti ting ng (&thi thinking) nking) Rati tionally

  • nally

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

  • they act appropriately given goals and circumstances
  • they are flexible to changing environments and goals
  • they learn from experience
  • they make appropriate choices given perceptual and

computational limitations (sometimes they act without thinking!)

  • They gather

r inform rmati ation

  • n (if cost less than expected gain)
slide-25
SLIDE 25

CPSC 322, Lecture 1 Slide 25

Acti ting ng Humanly anly

The original test involved typing back and forth; the `To Total l Tu Turing Te Test includes a video signal to test perception too

  • But... is acting just like a person what we really want?
  • For example, again, don't people often do things that we

don't don't consider intelligent?

The Tu Turing g Te 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

ent wh when people can't t tell a co computer uter apart from m other r people