32
Can Machines Think? Rob Kremer Department of Computer Science University of Calgary

Can Machines Think? Rob Kremer Department of Computer Science University of Calgary

  • View
    213

  • Download
    0

Embed Size (px)

Citation preview

Can Machines Think?

Rob Kremer

Department of Computer Science

University of Calgary

22

IntelligenceIntelligence

What is intelligence???

g

33

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.

?

g

44

IntelligenceIntelligence

Add vision and robotics to get the total Turing test.

g

55

Weak and Strong AI ClaimsWeak and Strong AI Claims

Weak AI:– Machines can be made

to act as if they were intelligent

Weak AI:– Machines can be made

to act as if they were intelligent

Strong AI:–Machines that act intelligently have real, conscious minds.

Strong AI:–Machines that act intelligently have real, conscious minds.

g

66

What is Intelligence?What is Intelligence?

The Chinese Room

g

77

What is Intelligence?What is Intelligence?

Replacing the brain

g

88

What is AI?What is AI?

g

99

How do we classify research as AI?How do we classify research as AI?

g

1010

Approaches to AIApproaches to AI

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

g

1111

LearningLearning

Explanation– Discovery – Data Mining

No Explanation– Neural Nets– Case Based Reasoning

g

1212

Learning: ExplanationLearning: Explanation

Cases to rules

g

1313

Learning: No ExplanationLearning: No Explanation

Neural nets

Doctor, doctor, I have a runny nose!

You’re going to die.

*ULP*! Why do you say

that??? No idea. The Neural Net

said so.g

1414

Approaches to AIApproaches to AI

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

g

1515

Rule-Based SystemsRule-Based Systems

Logic Languages– Prolog, Lisp

Knowledge bases Inference engines

g

1616

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)?

X

g

1818

Approaches to AIApproaches to AI

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

g

2020

Search: GamesSearch: Games

9!+1 = 362,880 nodes

g

2121

Approaches to AIApproaches to AI

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

g

2222

Approaches to AIApproaches to AI

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

g

2323

Ability-Based AreasAbility-Based Areas

Computer vision Natural language recognition Natural language generation Speech recognition Speech generation Robotics

g

2424

Natural Language: TranslationNatural Language: Translation

“The spirit is strong, but the flesh is weak.”

→ Translate to Russian

“Дух сильн, но плоть слаба.”

← Translate back to English

“The vodka is great, but the meat is rancid!”

g

2525

Natural Language RecognitionNatural Language Recognition

g

2626

Natural Language RepresentationNatural Language Representation

“Tom believes Mary wants to marry a sailor.”

g

2727

Approaches to AIApproaches to AI

Learning Rule-Based

Systems Search Planning Ability-Based Areas Robotics Agents

Learning Rule-Based

Systems Search Planning Ability-Based Areas Robotics Agents

RoboCup Challenge RoboCup Game

g

2828

Approaches to AIApproaches to AI

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

Learning Rule-Based Systems Search Planning Ability-Based Areas Robotics Agents

g

2929

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)

gg

3030

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

g

3131

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? g

3232

Happy Birthday,Shelby!

3333

QuickTime™ and a decompressor

are needed to see this picture.

g

3434

QuickTime™ and a decompressor

are needed to see this picture.

g