Download - 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary
![Page 1: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/1.jpg)
1
Artificial IntelligenceArtificial Intelligence
Rob Kremer
Department of Computer Science
University of Calgary
![Page 2: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/2.jpg)
2
What is AI?What is AI?
How doesthe humanbrain work?
How do weemulate the
human brain?
Who cares? Let’sdo some cool and
useful stuff!
How do wecreate
intelligence?What isintelligence?
![Page 3: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/3.jpg)
3
How do we classify research as AI?How do we classify research as AI?
Does itinvestigatethe brain?
If we don’t know howit works, then it’s AI.
When we find outhow it works, it’s not
AI anymore…
Is itintelligent?Does it
investigateintelligence?
Does it emulatethe brain?
![Page 4: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/4.jpg)
4
Approaches to AIApproaches to AI
Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents
![Page 5: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/5.jpg)
5
LearningLearning
Explanation– Discovery – Data Mining
No Explanation– Neural Nets– Case Based Reasoning
![Page 6: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/6.jpg)
6
Learning: ExplanationLearning: Explanation
Cases to rules
![Page 7: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/7.jpg)
7
Learning: No ExplanationLearning: No Explanation
Neural nets
![Page 8: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/8.jpg)
8
Approaches to AIApproaches to AI
Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents
![Page 9: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/9.jpg)
9
Rule-Based SystemsRule-Based Systems
Logic Languages– Prolog, Lisp
Knowledge bases Inference engines
![Page 10: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/10.jpg)
10
Rule-Based Languages: PrologRule-Based Languages: Prolog
Father(abraham, isaac). Male(isaac).Father(haran, lot). Male(lot).Father(haran, milcah). Female(milcah).Father(haran, yiscah). Female(yiscah).
Son(X,Y) Father(Y,X), Male(X).Daughter(X,Y) Father(Y,X), Female(X).
Son(lot, haran)?
![Page 11: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/11.jpg)
11
RuleBasedSystems
RuleBasedSystems
KRS
![Page 12: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/12.jpg)
12
Approaches to AIApproaches to AI
Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents
![Page 13: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/13.jpg)
13
SearchSearch
“All AI is search”– Game theory– Problem spaces
Every problem is a “virtual” tree of all possible (successful or unsuccessful) solutions.
The trick is to find an efficient search strategy.
![Page 14: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/14.jpg)
14
Search: Game TheorySearch: Game Theory
9!+1 = 362,880
![Page 15: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/15.jpg)
15
Approaches to AIApproaches to AI
Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents
![Page 16: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/16.jpg)
16
Approaches to AIApproaches to AI
Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents
![Page 17: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/17.jpg)
17
Ability-Based AreasAbility-Based Areas
Computer vision Natural language recognition Natural language generation Speech recognition Speech generation Robotics
![Page 18: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/18.jpg)
18
Natural Language: TranslationNatural Language: Translation
“The spirit is strong, but the flesh is weak.”
Translate to Russian Translate back to English
“The vodka is great, but the meat is rancid!”
![Page 19: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/19.jpg)
19
Natural Language RecognitionNatural Language Recognition
You give me the gold
pronounn
verb pronound
article noun
VP NP
VP
NP
VP
NP
sentencew
PERSON:Joe
PERSON:FredTRANSACTION
GOLD: X
REPT
OBJ
AGNT
Audio
Words
Syntax
Context
Semantics
![Page 20: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/20.jpg)
20
Natural Language RecognitionNatural Language Recognition
PERSON:Tom
BELIEF
PERSON:Mary
WANT
T MARRY SAILOR
SITUATION:
PROPOSITION:
EXPR
EXPR
AGNT
PTNT
PTNT
PTNT
“Tom believes Mary wants to marry a sailor.”
![Page 21: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/21.jpg)
21
Approaches to AIApproaches to AI
Learning Rule-Based
Systems Search Planning Ability-Based Areas Robotics Agents RoboCup Challenge RoboCup Game
![Page 22: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/22.jpg)
22
Approaches to AIApproaches to AI
Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents
![Page 23: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/23.jpg)
23
Agent CommunicationAgent Communication
AliceAlice BobBob
(performative: request, content: attend(Bob,x))Can you
attend this meeting?
(performative: agree, content: attend(Bob,x))Sure...
(performative: inform, content: attend(Bob,x))
I’m here
(performative: confirm, content: attend(Bob,x))Thanks for coming.
(performative: ack, content: attend(Bob,x))(nod)
(performative: ack, content: attend(Bob,x))
(nod)(performative: ack, content: attend(Bob,x))
(nod)
![Page 24: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/24.jpg)
24
Agent CommunicationAgent Communication
reply-propose-discharge(Alice,Bob,x)
act(Bob,Alice,x)
propose-discharge(Bob,Alice,x)
Alice Bob
request
inform
reply
agree
inform ack
propose-discharge
done
reply
inform ack
reply-propose-discharge
confirm
reply
informack
reply(Bob,Alice,x)
ack(Bob,Alice,x)
ack
ack(Bob,Alice,x)
ack
ack(Alice,Bob,x)
ack
ack(Alice,Bob,x)
ack
![Page 25: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/25.jpg)
25
IntelligenceIntelligence
Turing Test: A human communicates with a computer via a teletype. If the human can’t tell he is talking to a computer or another human, it passes.– Natural language processing– knowledge representation– automated reasoning– machine learning
Add vision and robotics to get the total Turing test.
![Page 26: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/26.jpg)
26
Weak and Strong AI ClaimsWeak and Strong AI Claims
Weak AI:– Machines can be made to act as if they
were intelligent. Strong AI:
– Machines that act intelligently have real, conscious minds.
![Page 27: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/27.jpg)
27
What is Intelligence?What is Intelligence?
The Chinese Room
`
?
!
![Page 28: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/28.jpg)
28
What is Intelligence?What is Intelligence?
The Chinese Room
`
?
!
![Page 29: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/29.jpg)
29
What is Intelligence?What is Intelligence?
Replacing the brain
![Page 30: 1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary](https://reader030.vdocument.in/reader030/viewer/2022032800/56649d2a5503460f949ff58f/html5/thumbnails/30.jpg)
30
How far have we got?How far have we got?
Our best systems have the intelligence of a frog
Mind you, how many frogs spend all their intelligence controlling a nuclear power plant?