PPTX

bouncerarcheryAI and Robotics

Nov 14, 2013 (3 years and 6 months ago)

65 views

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

1

Welcome to


CS 470/670



Introduction to

Artificial Intelligence


Fall 2012


Instructor: Marc Pomplun

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

2

Instructor


Marc Pomplun

Office:



S
-
3
-
171

Lab:




S
-
3
-
135

Office Hours:



Mondays 5:30pm


7:00pm


Wednesdays 4:00pm


5:30pm

Phone:



287
-
6443 (office)





287
-
6485 (lab)


E
-
Mail:



marc@cs.umb.edu

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

3

The Visual Attention Lab

Eye movement research

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

4

The new EyeLink
-
2K System

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

5

Example: Distribution of Visual Attention

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

6

Selectivity in Complex Scenes

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

7

Selectivity in Complex Scenes

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

8

Selectivity in Complex Scenes

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

9

Selectivity in Complex Scenes

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

10

Selectivity in Complex Scenes

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

11

Selectivity in Complex Scenes

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

12

Modeling of Brain Functions

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

13

Modeling of Brain Functions

unit and connection

in the interpretive network

unit and connection

in the gating network

unit and connection

in the top
-
down bias network

l

a

y

e

r



l

+

1

l

a

y

e

r



l



-

1

l

a

y

e

r



l

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

14

Computer Vision:

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

15

Human
-
Computer Interfaces:

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

16

Now back to CS 470/670:

Course Kit
:



Nils J. Nilsson,

Artificial Intelligence: A New
Synthesis,
Morgan Kaufmann 1998, ISBN 1
-
55860
-
467
-
7.


David M. Skapura,
Building Neural Networks,
Addison Wesley 1996, ISBN 0
-
201
-
53921
-
7


On the Web:

http://www.cs.umb.edu/~marc/cs470/

(contains all kinds of course information and also my
slides in PPT, PDF and HTML formats, updated
after

each session)

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

17

Your Evaluation


4
sets of
exercises




software projects:





25%

non
-
programming questions:



10%


midterm
(1.5 hours)







25%


final
exam (2.5 hours)

40%


September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

18

Grading



95%: A



90%: A
-



74%: C+



70%: C



66%: C
-



86%: B+



82%: B



78%: B
-



62%: D+



56%: D



50%: D
-



50%: F

For the assignments, exams and your course grade,
the following scheme will be used to convert
percentages into letter grades:

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

19

Complaints about Grading

If you think that the grading of your

assignment or exam was unfair,



write down your complaint (handwriting is OK),



attach it to the assignment or exam,



and give it to me or put it in my mailbox.

I will re
-
grade the
whole

exam/assignment and
return it to you in class.

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

20

Artificial Intelligence (AI)

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

21

Natural Intelligence

Before we
talk about “intelligent

machines,
let us first
consider examples of intelligence that we find in
nature.


Of course there we will find many different levels of
intelligence, cognitive abilities, and consciousness.


We will start with very basic abilities and make our
way towards the highest forms of intelligence that are
currently known to us.

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

22

Viruses


not considered to be
alive


do not reproduce on their own, but make bacteria
produce copies of themselves


no learning in individual viruses; only “evolutionary
learning”

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

23

Bacteria


are considered to be
alive


reproduce by splitting up into two organisms


capable of some simple learning that allows them to
move towards favorable environments

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

24

Insects


capable of learning and memorizing


primitive social interactions (trail of pheromones)


simple visual and olfactory perception (compound
eyes)


coordinated movements of legs to master different
types of terrains

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

25

Reptiles


good capability of vision (eyeballs, eye
movements)


able to learn certain behaviors


hunting abilities


still very primitive social interactions

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

26

Higher Mammals


very powerful senses


produce sounds but no language


complex social interactions


probably consciousness and basic feelings that are
related to our own

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

27

Non
-
Human Primates


very human
-
like genetic makeup and behaviors


produce different sounds with different meanings


capable of learning symbolic “language”


probably consciousness, self
-
awareness and basic
feelings at the level of a human kid

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

28

Humans


complex social behaviors


able to learn high
-
level syntactic languages


extremely long phase of learning (upbringing)


consciousness, self
-
awareness, abstract thinking


awareness of past and future, planning capability

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

29

Robots (Current Stage)


built by humans


coordinated body movements


little learning capabilities


no real social interaction or language


no consciousness or self
-
awareness

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

30

Levels of Artificial Intelligence

Today’s computers can do many well
-
defined tasks
(for example, arithmetic operations), much faster and
more accurate than human beings.

However, the computers’ interaction with their
environment is not very sophisticated yet.

How can we test whether a computer has reached
the general intelligence level of a human being?

Turing Test:

Can a computer convince a human
interrogator that it is a human?

But before thinking of such advanced kinds of
machines, we will start developing our own extremely
simple “intelligent” machines.

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

31

AI


The History

• AI is nearly as old as computing

• 1941 Konrad Zuse, Germany, general purpose
computer

• 1943 Britain (Turing and others) Colossus, for
decoding

• 1945 ENIAC, US. John von Neumann a consultant

• 1956 Dartmouth Conference organized by John
McCarthy (inventor of LISP)

• The term Artificial Intelligence was coined at
Dartmouth, which was intended as a two month
study.

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

32

AI


The Achievements


Robots make cars in all advanced countries.

• Reasonable machine translation is available for a
large range of foreign web pages.

• Computers land 200 ton jumbo jets unaided every
few minutes.

• Search systems like Google are not perfect but
provide very effective information retrieval

• Robots cut slots for hip joints better than surgeons.

• The chess program Deep Blue beat world champoin
Kasparov in 1997.

• Medical expert systems can outperform doctors in
many areas of diagnosis.

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

33

AI


A Comment

Despite all these achievements, one of the major
philosophers of Cognitive Science wrote:


“… the failure of artificial intelligence to produce
successful simulation of routine commonsense
cognitive competences is notorious, not to say
scandalous. We still don't have the fabled machine
that can make breakfast without burning down the
house; or the one that can translate everyday English
into everyday Italian, or the one that can summarize
texts..”
(Jerry Fodor, The Mind doesn’t Work that
Way, 2000, p.37).

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

34

What is Artificial Intelligence?


The use of computer programs and programming
techniques to cast light on the principles of
intelligence in general and human thought in
particular (Boden)

• The study of intelligence independent of its
embodiment in humans, animals or machines
(McCarthy)

• The pursuit of metaphysics by other means
(Longuet
-
Higgins)

• AI is the study of how to do things which at the
moment people do better (Rich & Knight)

• AI is the science of making machines do things that
would require intelligence if done by men. (Minsky)

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

35

What is Artificial Intelligence?

One of major divisions in AI (and you can see it in the
definitions on the previous slide) is between



Those who think AI is the only serious way of finding


out how
we

work (since opening heads does not yet


give much insight into this) and


• Those who want computers to do very smart


things,
independently

of how we work.


This is the important distinction between

Cognitive Scientists

vs.
Engineers
.

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

36

Symbolism vs. Connectionism

There is another major division in the field of Artificial
Intelligence:




Symbolic AI

represents information through


symbols and their relationships. Specific Algorithms


are used to process these symbols to solve


problems or deduce new knowledge.



Connectionist AI

represents information in a


distributed, less explicit form within a network.


Biological processes underlying learning, task


performance, and problem solving are imitated.

September 5, 2012

Introduction to Artificial Intelligence
Lecture 1: What is Artificial Intelligence?

37

The Plan

In this course, we will first
explore symbolic AI (the
“traditional” approach) and then
look at connectionist AI (artificial
neural networks).

I will not be around next week,
instead Nick Wang from my lab,
a great AI expert, will teach you
a lot of interesting things in the
next two lectures.