Introduction to intelligent systems - Computer Science

wonderfuldistinctΤεχνίτη Νοημοσύνη και Ρομποτική

16 Οκτ 2013 (πριν από 3 χρόνια και 11 μήνες)

85 εμφανίσεις

1

Artificial Intelligence

Past, Present, and Future


Olac Fuentes

Computer Science Department

UTEP

Artificial Intelligence

A definition:


AI is the science and engineering of making
intelligent machines

2

Artificial Intelligence

A definition:


AI is the science and engineering of making
intelligent machines


But, what is intelligence?


A very general mental capability that, among other
things, involves the ability to reason, plan, solve
problems, think abstractly, comprehend complex
ideas, learn quickly, and learn from experience.

3

Artificial Intelligence

Another definition:


AI is the science and engineering of making
machines that are capable of:


Reasoning


Representing knowledge


Planning


Learning


Understanding (human) languages


Understanding their environment


4

Old Times

The pursuit of “General AI”

Objective: Build a machine that exhibits ALL
of the AI features

5

Old Times


The Turing Test

How do we know when AI research has
succeed?

When a program that can consistently pass the
Turing test is written.

6

Old Times


The Turing Test

A human judge engages in a natural
language conversation with one
human and one machine, each of
which try to appear human; if the
judge cannot reliably tell which is
which, then the machine is said to
pass the test.

7

Old Times


The Turing Test

Problems with the Turing test:


Human intelligence vs. general intelligence


Computer is expected to exhibit undesirable
human behaviors


Computer may fail for being too smart


Real intelligence vs. simulated intelligence


Do we really need a machine that passes it?


Too hard!


Very useful applications can be
built that don’t pass the Turing test


8

More Recent Research

Goal: Build “intelligent” programs that are useful for a
particular task

Normally restricted to one target intelligent behavior.

Thus AI has been broken into several sub
-
areas:


Machine learning


Computer vision


Natural language processing


Robotics


Knowledge representation and reasoning

9

What has AI done for us?

State of the Art

It has provided computers that are able to:


Learn (some simple concepts and tasks)


Understand images (of restricted predefined types)


Understand human languages (some of them,
mostly written, with limited vocabularies)


Allow robots to navigate autonomously (in
simplified environments)


Reason (using brute force, in very restricted
domains)

10

Machine Learning

The key enabling technology of AI

Problem Solving in Computer Science

11

Machine Learning

The key enabling technology of AI

Problem Solving in Computer Science


Traditional Approach


Write a detailed sequence of instructions (a program)
that tells the computer how to solve the problem.

12

Machine Learning

The key enabling technology of AI

Problem Solving in Computer Science


Traditional Approach


Write a detailed sequence of instructions (a program)
that tells the computer how to solve the problem.


Machine Learning Approach


Give the computer examples of desired results and let it
learn how to solve the problem.

13

Machine Learning

The key enabling technology of AI

Problem Solving in Computer Science


Traditional Approach


Write a detailed sequence of instructions (a program)
that tells the computer how to solve the problem.


Machine Learning Approach


Give the computer examples of desired results and let it
learn how to solve the problem.


Advantage
: It allows to solve problems that we can’t
solve with the traditional approach

14

Machine Learning

The key enabling technology of AI

Problem Solving in Computer Science


Traditional Approach


Write a detailed sequence of instructions (a program)
that tells the computer how to solve the problem.


Machine Learning Approach


Give the computer examples of desired results and let it
learn how to solve the problem.


Advantage
: It allows to solve problems that we can’t
solve with the traditional approach


Most applications in other AI areas are based on machine
learning

15

Machine Learning

The key enabling technology of AI

Problem Solving in Computer Science


Traditional Approach


Write a detailed sequence of instructions (a program)
that tells the computer how to solve the problem.


Machine Learning Approach


Give the computer examples of desired results and let it
learn how to solve the problem.


Advantage
: It allows to solve problems that we can’t
solve with the traditional approach


Most applications in other AI areas are based on machine
learning

16

Computers that learn

How?

Very active research area


17

Computers that learn

How?

Very active research area



Extract statistical regularities from data



18

Computers that learn

How?

Very active research area



Extract statistical regularities from data



Find decision boundaries


19

Computers that learn

How?

Very active research area



Extract statistical regularities from data



Find decision boundaries



Find decision rules


20

Computers that learn

How?

Very active research area



Extract statistical regularities from data



Find decision boundaries



Find decision rules



Imitate human brain


21

Computers that learn

How?

Very active research area



Extract statistical regularities from data



Find decision boundaries



Find decision rules



Imitate human brain



Imitate biological evolution



22

Computers that learn

How?

Very active research area



Extract statistical regularities from data



Find decision boundaries



Find decision rules



Imitate human brain



Imitate biological evolution



Combine several approaches


23

What has AI done for us?

It has provided computers that are able to:


Learn (some simple concepts and tasks)


Understand images (of restricted predefined types)


Understand human languages (some of them,
mostly written, with limited vocabularies)


Allow robots to navigate autonomously (in
simplified environments)


Reason (using brute force, in very restricted
domains)

24

What has AI done for us?

Machine Learning


Netflix movie recommender system

Very active research area



Extract statistical regularities from data



Find decision boundaries



Find decision rules



Imitate human brain



Imitate biological evolution



Combine several approaches


25

What has AI done for us?

Machine Learning


Netflix movie recommender system

Idea:


After returning a movie, user assigns a grade to it
(from 1 to 5)


Given (millions) of records of users, movies and
grades, and the pattern of grades assigned by the
user, the system presents a list of movies the user
is likely to grade highly


27

What has AI done for us?

Robotics
-

Stanley, a self
-
driving car

28

What has AI done for us?


Robotics
-

Stanley, a self
-
driving car

What does Stanley learn?

A mapping from sensory inputs to driving commands


29

What has AI done for us?


Robotics
-

Lexus self
-
parking system

30

What has AI done for us?

Computer Vision
-

Face Detecting
Cameras

31

What has AI done for us?

Computer Vision
-

Face
Detecting Cameras

What has AI done for us?

Reasoning

Successful applications:


Commercial planning systems


Chess playing programs


Checkers playing programs


Optimal solution to Rubik’s cube



What has AI done for us?


Reasoning

The
Zohirushi

Neuro

Fuzzy
® Rice Cooker & Warmer features advanced
Neuro

Fuzzy
® logic technology, which allows the rice cooker to 'think' for itself and
make fine adjustments to temperature and heating time to cook perfect rice
every time.

What has AI done for us?

Natural language processing

Successful applications:


Dictation systems


Text
-
to
-
speech systems


Text classification


Automated summarization


Automated translation



What has AI done for us?

Natural language processing

Automated Translation

Original English Text:

The Dodgers became the fifth team in modern major league
history to win a game in which they didn't get a hit,
defeating the Angels 1
-
0. Weaver's error on a slow roller led
to an unearned run by the Dodgers in the fifth.


What has AI done for us?

Natural language processing

Automated Translation

Original English Text:

The Dodgers became the fifth team in modern major league
history to win a game in which they didn't get a hit,
defeating the Angels 1
-
0. Weaver's error on a slow roller led
to an unearned run by the Dodgers in the fifth.

Translation to Spanish
(by Google
-

2008)

Los
Dodgers

se convirtió en el quinto equipo en la moderna
historia de las ligas mayores para ganar un juego en el que
no obtener una respuesta positiva, derrotando a los Ángeles
1
-
0.
Weaver's

error en un lento rodillo dado lugar a un
descontados no correr por la
Dodgers

en el quinto.


What has AI done for us?

Natural language processing

Automated Translation

Original English Text:

The Dodgers became the fifth team in modern major league
history to win a game in which they didn't get a hit,
defeating the Angels 1
-
0. Weaver's error on a slow roller led
to an unearned run by the Dodgers in the fifth.

Translation to Spanish
(by Google
-

2010)

Los
Dodgers

se convirtió en el quinto equipo en la historia
moderna de las Grandes Ligas en ganar un partido en el que
no obtuvo una respuesta positiva, derrotando a los
Angelinos 1
-
0.

De error de
Weaver

en un rodillo lento
condujo a una carrera sucia por los
Dodgers

en el quinto.

What has AI done for us?

Natural language processing

Automated Translation

Translation to Spanish
(by Google)

Los
Dodgers

se convirtió en el quinto equipo en la moderna
historia de las ligas mayores para ganar un juego en el que
no obtener una respuesta positiva, derrotando a los Ángeles
1
-
0.
Weaver's

error en un lento rodillo dado lugar a un
descontados no correr por la
Dodgers

en el quinto.



What has AI done for us?

Natural language processing

Automated Translation

Translation to Spanish
(by Google
-

2008)

Los
Dodgers

se convirtió en el quinto equipo en la moderna
historia de las ligas mayores para ganar un juego en el que
no obtener una respuesta positiva, derrotando a los Ángeles
1
-
0.
Weaver's

error en un lento rodillo dado lugar a un
descontados no correr por la
Dodgers

en el quinto.

Translation back to English
(by Yahoo)

The Dodgers became the fifth equipment in the modern history
of the leagues majors to gain a game in which not to obtain
a positive answer, defeating to Los Angeles 1
-
0. Weaver' s
error in a slow given rise roller to discounting not to run by
the Dodgers in fifth.



What has AI done for us?

Natural language processing

Automated Translation

Translation to Spanish
(by Google
-

2010)

Los
Dodgers

se convirtió en el quinto equipo en la historia
moderna de las Grandes Ligas en ganar un partido en el que
no obtuvo una respuesta positiva, derrotando a los
Angelinos 1
-
0.

De error de
Weaver

en un rodillo lento
condujo a una carrera sucia por los
Dodgers

en el quinto.

Translation back to English
(by Yahoo)

The Dodgers became the fifth equipment in the modern history
of the Great Leagues in gaining a party in which it did not
obtain a positive answer, defeating to the Angelinos 1
-
0.

Of
error of Weaver in a slow roller it lead to a dirty race by the
Dodgers in fifth.


The Future of AI


The Future of AI

Making predictions is hard, especially about the future
-

Yogi
Berra



The Future of AI

Making predictions is hard, especially about the future
-

Yogi
Berra


But…


Continued progress expected


Greater complexity and autonomy


New enabling technology
-

Metalearning


Once human
-
level intelligence is attained, it will be quickly
surpassed


Conclusions


Conclusions


Artificial Intelligence has made a great deal of progress
since its inception in the 1950s

Conclusions


Artificial Intelligence has made a great deal of progress
since its inception in the 1950s


The goal of general AI has been abandoned (at least
temporarily)

Conclusions


Artificial Intelligence has made a great deal of progress
since its inception in the 1950s


The goal of general AI has been abandoned (at least
temporarily)


Useful applications have appeared in all subfields of AI,
including: Machine learning, computer vision, robotics,
natural language processing and knowledge representation

Conclusions


Artificial Intelligence has made a great deal of progress
since its inception in the 1950s


The goal of general AI has been abandoned (at least
temporarily)


Useful applications have appeared in all subfields of AI,
including: Machine learning, computer vision, robotics,
natural language processing and knowledge representation


The field continues to evolve rapidly

Conclusions


Artificial Intelligence has made a great deal of progress
since its inception in the 1950s


The goal of general AI has been abandoned (at least
temporarily)


Useful applications have appeared in all subfields of AI,
including: Machine learning, computer vision, robotics,
natural language processing and knowledge representation


The field continues to evolve rapidly


Increased complexity and unpredictability of AI programs
will raise important ethics issues and concerns