ai - introduction
DESCRIPTION
AI - Introduction. Bertil Ekdahl [email protected]. What is AI?. It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, - PowerPoint PPT PresentationTRANSCRIPT
![Page 2: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/2.jpg)
2
It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable.
What is AI?
John McCarthy, http://www-formal.stanford.edu/jmc/whatisai/
![Page 3: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/3.jpg)
3
When did it start?
• Alan Turing – 1947 lecture on intelligent machines.– 1950 article: Computing Machinery and
Intelligence.
![Page 4: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/4.jpg)
4
The Turing Test
(Borrowed from Ola Flygt.)
![Page 5: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/5.jpg)
5Penrose, Roger, “The Emperor’s New Mind”
A Turing Machine
![Page 6: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/6.jpg)
6
Two symbols where B means “blank” and 1 is the tally symbol.
{ }1,B
![Page 7: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/7.jpg)
7
ENIAC(Electronic Numerical Integrator And Calculator)
![Page 8: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/8.jpg)
8
EDVAC(Electronic Discrete Variable Automatic Computer)
![Page 9: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/9.jpg)
9
Dartmouth Artificial Intelligence (AI) Conference
• We propose that a 2 month, 10 man study of artificial intelligence be carried out during the summer of 1956 at Dartmouth College in Hanover, New Hampshire.
• The study is to proceed on the basis of the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. An attempt will be made to find how to make machines use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves.
• Dartmouth AI Project proposal: J. McCarthy et al.; Aug. 31, 1955.
(http://www-formal.stanford.edu/jmc/history/dartmouth.html)
![Page 10: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/10.jpg)
10
Why such a conjecture?
… every aspect of learning […] be so
precisely described that a machine
can be made to simulate it.
Tabula rasa
![Page 11: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/11.jpg)
11
But the human intellect, which is the lowest in the order of intellects and the most removed from the perfection of the Divine intellect, is in potency with regard to things intelligible, and is at first "like a clean tablet on which nothing is written", as the Philosopher [Aristotle] says. (Thomas Aquinas, Summa Theologica 1.79.2, 1265 - 1274)
![Page 12: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/12.jpg)
12
Connectionism Rumelhart & McClelland: generic
associationist networks, subjected
to massive amounts of training, could explain all of cognition.
![Page 13: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/13.jpg)
13
Rumelhart & McClelland was left with the answer: Why is people smarter than rats?Answer: [The] question does seem a bit puzzling. […] another aspect to the difference […] is that the human environment includes other people and the CULTURAL devices that they have developed to organize their thinking process.(1986)
A problem
![Page 14: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/14.jpg)
14
Why such a conjecture?…make machines use language, form abstractions and concepts …
No difference between formal language (programming language) and natural language?
![Page 15: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/15.jpg)
15
Everything is a question of representation?
![Page 16: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/16.jpg)
16
Roman digits
III
XV
![Page 17: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/17.jpg)
17
Binary digits
11
1111
![Page 18: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/18.jpg)
18
2
367654983274
10
100100...1shift out
![Page 19: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/19.jpg)
19
Time
2h 30min 15s + 3h 45min 37s =?
![Page 20: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/20.jpg)
20
Fifty-fiveFemtiofemFünfundfünfzigFemoghalvtreds
![Page 21: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/21.jpg)
21
What is a Knowledge Representation?
• A KR is a Surrogate
• A KR is a Set of Ontological Commitments
• A KR is a Fragmentary Theory Of Intelligent Reasoning
• A KR is a Medium for Efficient Computation
• A KR is a Medium of Human Expression
(R. Davis, H. Shrobe, and P. Szolovits. What is a Knowledge Representation? AI Magazine, 14(1):17-33, 1993).
![Page 22: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/22.jpg)
22
Knowledge representation in AI
• Logic
• Semantic nets
• Conceptual graphs
• Neural nets
• Object oriented methods
![Page 23: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/23.jpg)
23
Logic
Production system: IF … THEN
IF you have pain in your backAND you have eaten many PanocodeTHEN examine your bile.
![Page 24: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/24.jpg)
24
Pain in your back?
Yes NoEatenPanocode?
![Page 25: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/25.jpg)
25
G: Men are all alike.P: IN WHAT WAY?
G: They’re always bugging us about something or other.P: CAN YOU THINK OF A SPECIFIC EXAMPLE?
G: Well, my boyfriend made me come here.P: YOUR BOYFRIEND MADE YOU COME HERE?
G: He says I’m depressed much of the time.P: I AM SORRY TO HERE THAT YOU ARE DEPRESSED.
G: It’s true. I am unhappy.P: DO YOU THINK COMING HERE WILL HELP YOU NOT TO BE UNHAPPY?
G: I need some help, that much seems certain.P: WHAT WOULD IT MEAN TO YOU IF YOU GOT SOME HELP?
G: Perhaps I could learn to get along with my mother.P: TELL ME MORE ABOUT YOUR FAMILY.
![Page 26: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/26.jpg)
26
(I remember X) ---> (Why do you remember X just now?)
Person: I remember my mother.ELIZA: Why do you remember your mother just now?
(My {family-member} Y me) ---> (Who else in your family Y you?)
Person: My father hates me.ELIZA: Who else in your family hates you?
Rules without left hand side.
ELIZA: Can you elaborate on that for me?, or
ELIZA: That is very interesting. Why do you say that?
![Page 27: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/27.jpg)
27
Logic goes beyond IF … THEN-rules
The author of the Iliad wrote the Odyssey; therefore someone wrote both the Iliad and the Odyssey.
No one admires anyone who admires everyone who admires someone.
![Page 28: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/28.jpg)
28
Semantic nets
![Page 29: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/29.jpg)
29
Mammal BearAnimal
FishWater
Whale
Fur
Vertebra
Cat
isa
isa
lives in
lives in
isa
has
isa
has
has
![Page 30: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/30.jpg)
30
Nixon
Pacifist
Quaker Republican
isa isa
isa isa
![Page 31: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/31.jpg)
31
CG: John is going to Boston by bus.
Conceptual Graph
![Page 32: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/32.jpg)
32
/* schema facts */ man::person. woman::person. person[hasFather=>man].person[hasMother=>woman].
/* facts */ abraham:man. sarah:woman. isaac:man[hasFather->abraham; hasMother->sarah].
/* rules consisting of a rule head and a rule body */ FORALL X,Y X[hasSon->>Y] <- Y:man[hasFather->X].
/* query */ FORALL X,Y <- X:woman[hasSon->>Y[hasHasFather->abraham]].
Object method
![Page 33: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/33.jpg)
33
(John McCarthy, http://www-formal.stanford.edu/jmc/whatisai/)
Q. How far is AI from reaching human-level intelligence? When will it happen? A. A few people think that human-level intelligence can be achieved by writing large numbers of programs of the kind people are now writing and assembling vast knowledge bases of facts in the languages now used for expressing knowledge. However, most AI researchers believe that new fundamental ideas are required, and therefore it cannot be predicted when human level intelligence will be achieved.
![Page 34: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/34.jpg)
34
Why have we made limited progress in AI? Because we haven't developed sophisticated models of thinking, we need better programming languages and architectures, and we haven't focused on common sense problems that every normal child can solve.
(Minsky, 2002)
![Page 35: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/35.jpg)
35
What’s the problem?
Semantics
![Page 36: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/36.jpg)
36
Fifty-fiveFemtiofemFünfundfünfzigFemoghalvtreds
Roman: LV
Binary: 110111
Octal: 101101
Decimal: 55
![Page 37: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/37.jpg)
37
Susan saw the man in the park with a dog.
Susan saw the man in the park with a statue.
Susan saw the man in the park with a telescope
![Page 38: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/38.jpg)
38
Computer versus Common Sensehttp://video.google.com/videoplay?docid=-7704388615049492068
![Page 39: AI - Introduction](https://reader035.vdocument.in/reader035/viewer/2022062217/56814cfe550346895dba236d/html5/thumbnails/39.jpg)
39
END