Anda di halaman 1dari 31

Introduction to

Artificial Intelligence
Christian Jacob
Department of Computer Science University of Calgary

What is AI?
How does the human brain work? How do we emulate the human brain? How do we create intelligence?

What is intelligence?

Who cares? Lets do some cool and useful stuff!

How do we classify research as AI?


Does it investigate the brain? Does it investigate intelligence? Does it emulate the brain?

Is it intelligent?

If we dont know how it works, then its AI. When we find out how it works, its not AI anymore

Intelligence
The ability to learn and to cope. n The ability to contemplate, think, and reason. n Synonyms:
n
u Brain, brainpower, mentality, mother wit,

sense, wit
n

Related:
u Acumen, discernment, insight, judgment,

perspicacity, sagacity, wisdom

Intelligence
n

Turing Test: A human communicates with a computer via a teletype. If the human cant tell he is talking to a computer or another human, it passes.
u Natural language processing u knowledge representation u automated reasoning u machine learning

Add vision and robotics to get the total Turing test.

Weak and Strong AI Claims


n

Weak AI:
u Machines can be made to act as if they were

intelligent.
n

Strong AI:
u Machines that act intelligently have real,

conscious minds.

Approaches to AI
Searching n Learning n From Natural to Artificial Systems n Knowledge Representation and Reasoning n Expert Systems and Planning n Communication, Perception, Action
n

Search
n

All AI is search
u Game theory u Problem spaces

Every problem is a feature space of all possible (successful or unsuccessful) solutions. n The trick is to find an efficient search strategy.
n

Search: Game Theory

9!+1 = 362,880

Approaches to AI
Searching n Learning n From Natural to Artificial Systems n Knowledge Representation and Reasoning n Expert Systems and Planning n Communication, Perception, Action
n

Learning
n

Explanation
u Discovery u Data Mining

No Explanation
u Neural Nets u Case Based Reasoning

Learning: Explanation
n

Cases to rules

Learning: No Explanation
n

Neural nets

Approaches to AI
Searching n Learning n From Natural to Artificial Systems n Knowledge Representation and Reasoning n Expert Systems and Planning n Communication, Perception, Action
n

Approaches to AI
Searching n Learning n From Natural to Artificial Systems n Knowledge Representation and Reasoning n Expert Systems and Planning n Communication, Perception, Action
n

Rule-Based Systems
n

Logic Languages
u Prolog, Lisp

Knowledge bases n Inference engines


n

Rule-Based Languages: Prolog


Father(abraham, isaac). Father(haran, lot). Father(haran, milcah). Father(haran, yiscah). Male(isaac). Male(lot). Female(milcah). Female(yiscah).

Son(X,Y) Father(Y,X), Male(X). Daughter(X,Y) Father(Y,X), Female(X).

Son(lot, haran)?

Rule Based Systems


n

KRS

Approaches to AI
Searching n Learning n From Natural to Artificial Systems n Knowledge Representation and Reasoning n Expert Systems and Planning n Communication, Perception, Action
n

Approaches to AI
Searching n Learning n From Natural to Artificial Systems n Knowledge Representation and Reasoning n Expert Systems and Planning n Communication, Perception, Action
n

Ability-Based Areas
Computer vision n Natural language recognition n Natural language generation n Speech recognition n Speech generation n Robotics
n

Natural Language: Translation


The flesh is weak, but the spirit is strong
Translate to Russian Translate back to English

The food was lousy, but the vodka was great!

Natural Language Recognition


OBJ GOLD: X

Semantics Context

PERSON: Joe

REPT

TRANSACTION

AGNT

PERSON: Fred

sentence w VP NP Syntax pronoun n Words You VP verb VP NP pronoun d me article NP noun

give

the

gold

Audio

What is Intelligence?
n

Replacing the brain?

How far have we got?


n

Our best systems have the intelligence of a frog

What is Artificial Intelligence?


n

We will find out

Anda mungkin juga menyukai