Intro - Tamara L Berg

siennaredwoodIA et Robotique

23 févr. 2014 (il y a 3 années et 1 mois)

63 vue(s)

Introduction

Tamara Berg

CS 590
-
133 Artificial Intelligence

Many slides throughout the course adapted from Dan Klein, Stuart Russell,
Andrew Moore, Svetlana
Lazebnik
, Percy Liang, Luke
Zettlemoyer

Today


Course Info



What is AI?



History of AI



Current state of AI


Course Information


Instructor: Tamara Berg (
tlberg@cs.unc.edu
)


Office Hours: FB 236, Tues/Thurs 4:45
-
5:45pm


Course website:
http://tamaraberg.com/teaching/Spring_14/


Course mailing list:
comp590
-
133@
cs.unc.edu




TAs:
Shubham

Gupta &
Rohit

Gupta

TA office hours: TBD



Announcements, readings, schedule,
etc
, will all be posted to
the course webpage. Schedule may be modified as needed
over the semester. Check frequently!

Course Information


Textbook: “Artificial Intelligence A Modern Approach” Russell &
Norvig
, 3
rd

edition



Prerequisites:


Programming knowledge and data structures (COMP 401 and 410) are required


Reasonable familiarity with probability, algorithms, calculus also highly desired


There will be a lot of math and programming



Work & Grading


Readings (mostly from textbook)


5
-
6 assignments including written questions, programming, or both


2 midterms (approximate dates are on course website) and final exam


Grading will consist of 60% assignments, 40% exams. For borderline cases
participation
in class or via the mailing list may
also be considered.



Programming


Students are expected to know how to program.



Programming assignments will be in python


useful language
to know, used in many current AI courses, not too hard to pick
up given previous programming experience.



First week


install python on your laptops, do a python
tutorial



TAs will also hold drop in tutorials early next week (probably
Mon/Tues, times will be posted to website). Make sure to
attend if you’re new to python or want a refresher.

Course Information

Late policy:


Assignments must be turned in electronically by 11:59pm
on the listed due date.


Students
will be allowed 5 free homework late days of
their choice over the semester (you don't need to ask
ahead of time, just use them and we will keep track).


After
those are used late
homework
will be accepted
up
to 1 week late, with
a 10% reduction in value per day
late.



Course Information

Honor code:


Students are encouraged to complete the assignments in
groups of 2.


You may discuss problems at a high level with other
students in the class, but all
code and written responses
should
be original within your pair.


To
protect the integrity of the course, we will
actively
check
for
code or written
plagiarism (both from current
classmates and the internet).


Exams
will be closed book.

About me

1997
-
2001

Undergrad
at U.W. Madison

CS and Math

2001
-
2007

Grad at
U.C. Berkeley

Ph.D. in
CS

2007
-
2008

Postdoc at
Yahoo! Research

2008
-
2013

Assistant Prof
at SBU

2013
-

Assistant Prof
at UNC

My research
interests

Yellow lady’s slipper

leonberg

Image Classification

1000 classes

62.5% accuracy,
Krizhevsky

et al

Human
-
centric Computer Vision

Object Detection

20 object classes

39% accuracy,
Girshick

et al

Image Parsing

33 labels

55% accuracy,

Tighe

et al

Computer Vision

This is a picture of one
sky, one road and one
sheep. The gray sky is
over the gray road. The
gray sheep is by the gray
road.

Here we see one road,
one sky and one bicycle.
The road is near the blue
sky, and near the colorful
bicycle. The colorful
bicycle is within the blue
sky.

BabyTalk
: Generating natural language
image descriptions

This is a picture of two
dogs. The first dog is
near the second furry
dog.

Recognizing Clothing

Application: Pose Independent Retrieval

S
h
o
r
t
s

B
l
a
z
e
r

T
-
s
h
i
r
t

About you?


Undergrad/grad


Year


Major/Minors


Background in:


Programming


Calculus


Probability


Python


Sci
-
Fi AI

AI

Knowledge
representation

Planning

Learning

Natural
Language
Processing

Perception
(computer
vision, speech)

Reasoning

Motion &
Manipulation
(robotics)

Social
Intelligence

Creativity

What is AI?


Definitions of AI:




1.

Think
ing humanly

2.

Acting humanly

3.

Thinking Rationally

4. Acting rationally

AI definition 1: Thinking humanly


Need to study the
brain as an information
processing
machine: cognitive science and
neuroscience

AI definition 1: Thinking humanly

Can we build a brain?

AI definition 1: Thinking humanly


Can we build a brain?


The Turing Test







What capabilities would a computer need to have to pass the
Turing Test?


Natural language processing


Knowledge representation


Automated reasoning


Machine learning

AI definition 2: Acting humanly

A. Turing,
Computing machinery and intelligence
, Mind 59, pp. 433
-
460, 1950


Turing predicted that by the year 2000, machines would be able to fool 30%
of human judges for five minutes


Loebner prize


2008 competition:

each of
12
judges was given five minutes
to conduct simultaneous, split
-
screen conversations with
two hidden
entities (human and
chatterbot
). The winner,
Elbot

of Artificial
Solutions,

managed to fool
three of the
judges
into believing it was
human [
Wikipedia
]
.

The Turing Test


Success depends on deception!


Chatbots

can do well using “cheap tricks”


First example:
ELIZA

(1966)


Chinese room argument
: one may simulate
intelligence without having true intelligence
(more of a philosophical objection)

Turing Test: Criticism

A better Turing test?

http://
www.newyorker.com/online/blogs/elements/2013/08/why
-
cant
-
my
-
computer
-
understand
-
me.html

A better Turing test?


Multiple choice questions that can be easily
answered by people but cannot be answered
by computers using “cheap tricks”:



The
trophy would not fit in the brown
suitcase
because
it was so small.

What
was so
small?


T
he trophy


T
he
brown suitcase

H. Levesque,
On our best
behaviour
, IJCAI 2013

A better Turing test?


Multiple choice questions that can be easily
answered by people but cannot be answered
by computers using “cheap tricks”:



The
trophy would not fit in the brown
suitcase
because
it was so
large
.

What
was so
large
?


T
he trophy


T
he
brown suitcase

H. Levesque,
On our best
behaviour
, IJCAI 2013

A better Turing test?


Multiple choice questions that can be easily
answered by people but cannot be answered
by computers using “cheap tricks”:



The large ball crashed right through the
table
because
it was made of
styrofoam
.

What was made
of
styrofoam
?


The large ball


The
table

H. Levesque,
On our best
behaviour
, IJCAI 2013

A better Turing test?


Multiple choice questions that can be easily
answered by people but cannot be answered
by computers using “cheap tricks”:



The large ball crashed right through the
table
because
it was made of
steel
.

What was made
of
steel
?


The large ball


The
table

H. Levesque,
On our best
behaviour
, IJCAI 2013

A better Turing test?


Multiple choice questions that can be easily
answered by people but cannot be answered
by computers using “cheap tricks”:



Sam tried to paint a picture of shepherds
with
sheep
, but they ended up looking
like golfers
.
What looked like
golfers?


T
he shepherds


T
he
sheep

H. Levesque,
On our best
behaviour
, IJCAI 2013

A better Turing test?


Multiple choice questions that can be easily
answered by people but cannot be answered
by computers using “cheap tricks”:



Sam tried to paint a picture of shepherds
with
sheep
, but they ended up looking
like
rabbits
.
What looked like
rabbits
?


T
he shepherds


T
he
sheep

H. Levesque,
On our best
behaviour
, IJCAI 2013

A better Turing test?



Why are these questions hard for
computers??

H. Levesque,
On our best
behaviour
, IJCAI 2013

A better Turing test?


Advantages over standard Turing test


Test can be administered and graded by machine


Does not depend on human subjectivity


Does not require ability to generate English
sentences


Questions cannot be evaded using verbal dodges


Questions can be made “Google
-
proof”

H. Levesque,
On our best
behaviour
, IJCAI 2013

AI definition 3&4: Rationality


A
rational agent
acts to optimally achieve its goals


Goals are application
-
dependent and are
expressed in terms of the
utility of outcomes


Being rational means
maximizing your
(expected) utility


This definition of rationality only concerns the
decisions/actions that are made, not the cognitive process
behind them


In practice, utility optimization is subject to the agent’s
computational constraints (
bounded rationality

or
bounded
optimality
)

Utility maximization formulation


Advantages


Generality: goes beyond explicit reasoning, and
even human cognition altogether


Practicality: can be adapted to many real
-
world
problems


Naturally accommodates uncertainty


Amenable to good scientific and engineering
methodology


Avoids philosophy and psychology


Disadvantages?


History of AI

Image source

Origins of AI: Early excitement

1940s

First model of a neuron (W. S. McCulloch & W. Pitts)



Hebbian

learning rule



Cybernetics

1950s

Turing Test



Perceptrons

(F. Rosenblatt
)



Computer chess and checkers (C. Shannon, A. Samuel)



Machine
translation (Georgetown
-
IBM experiment)



Theorem
provers

(A. Newell and H. Simon,


H. Gelernter and N. Rochester)

1956

Dartmouth
meeting:
“Artificial Intelligence” adopted

Herbert Simon, 1957


“It is not my aim to surprise or shock you



but … there are now in the world

machines that think, that learn and that

create. Moreover, their ability to do these

things is going to increase rapidly until


in a visible future


the range of problems

they can handle will be coextensive with

the range to which human mind has been applied.
More
precisely: within 10 years a computer would be chess
champion, and an important new mathematical theorem
would be proved by a computer.




Simon’s prediction came true


but forty years later

instead of ten

Harder than originally thought


1966:
Eliza

chatbot

(
Weizenbaum
)



“ … mother …”


“Tell me more about your family”



1954:
Georgetown
-
IBM experiment


Completely automatic translation of more than sixty Russian
sentences into English


Only six grammar rules, 250 vocabulary words, restricted to
organic chemistry


Promised that machine translation would be solved in three to
five years (
press release
)


Automatic Language Processing Advisory Committee (ALPAC)
report (1966): machine translation has failed


“The spirit is willing but the flesh is weak.”



“The vodka is strong but the meat is rotten.”

Blocks world (1960s


1970s)

Larry Roberts
, MIT, 1963

???

History of AI: Taste of failure

1940s



First
model of a neuron (W. S. McCulloch & W. Pitts)




Hebbian

learning rule




Cybernetics


1950s



Turing
Test




Perceptrons

(F. Rosenblatt
)









Computer
chess and checkers (C. Shannon, A. Samuel)




Machine
translation (Georgetown
-
IBM experiment)




Theorem
provers

(A. Newell and H. Simon,




H
. Gelernter and N. Rochester)


Late 1960s

Machine translation deemed a failure




Neural nets deprecated (M.
Minsky

and S.
Papert
, 1969)*


Late 1970s

The first
“AI Winter”



*
A sociological study of the official history of the
perceptrons

controversy

History of AI to the present day

1980s



Expert systems boom


Late 1980s
-



Expert
system bust; the second “AI winter


Early 1990s



Mid
-
1980s



Neural networks and back
-
propagation


Late 1980s


Probabilistic reasoning on the ascent


1990s
-
Present

Machine learning everywhere





Big Data





Deep Learning

Building Smarter Machines: NY Times Timeline

AAAI Timeline

History of AI on Wikipedia

NY Times article

What accounts for recent successes in AI?


Faster computers


The IBM 704 vacuum tube machine that played chess
in 1958 could do about

50,000 calculations per
second


Deep Blue could do
50 billion calculations per second




a million times faster!


Dominance of statistical approaches, machine
learning


Big data


C
rowdsourcing

What can AI do today?

IBM Watson


http://www
-
03.ibm.com/innovation/us/watson/


NY Times article


Trivia demo


IBM Watson wins on Jeopardy

(February 2011)

S
elf
-
driving cars


Google’s self
-
driving car passes 300,000 miles

(Forbes, 8/15/2012)


Nissan pledges affordable self
-
driving car models by
2020


(CNET, 8/27/2013)


Natural Language


Speech technologies


Google voice search


Apple Siri





Machine translation


translate.google.com


Comparison of several translation systems


Vision


OCR, handwriting recognition


Face detection/recognition: many consumer
cameras,
Apple iPhoto


Visual search:
Google Goggles
,
search by image


Vehicle safety systems:
Mobileye

Mathematics


In 1996, a computer program written by researchers at
Argonne National Laboratory proved a mathematical
conjecture unsolved for decades


NY Times story
: “[The proof] would have been
called creative if a human had thought of it”


Mathematical software:

G
ames


IBM’s Deep
Blue defeated the reigning world chess
champion Garry Kasparov in
1997


1996: Kasparov Beats Deep Blue

“I could feel


I could smell


a new kind

of intelligence across the table.”


1997: Deep Blue Beats Kasparov

“Deep Blue hasn't proven anything.”



In 2007, checkers was “solved” (though checkers programs
had been beating the best human players for at least a
decade before then)


Science article

Logistics, scheduling, planning


During the 1991 Gulf War, US forces deployed an
AI logistics planning and scheduling program that
involved up to 50,000 vehicles, cargo, and people


NASA’s
Remote Agent

software operated the
Deep Space 1 spacecraft during two experiments
in May 1999


In 2004, NASA introduced the
MAPGEN

system to
plan the daily operations for the Mars Exploration
Rovers



Robotics


Mars rovers


Autonomous vehicles


DARPA Grand Challenge


Self
-
driving
cars


Autonomous helicopters


Robot soccer


RoboCup


Personal robotics


Humanoid robots


Robotic pets


Personal assistants?

Towel
-
folding robot


J.
Maitin
-
Shepard, M.
Cusumano
-
Towner, J. Lei and P.
Abbeel
,
Cloth Grasp Point Detection based
on Multiple
-
View Geometric Cues with Application to Robotic Towel Folding
, ICRA 2010


More clothes folding




YouTube Video

Outline of the Class


Part 1: Agents & Decisions


Fast search


Constraint satisfaction


Reinforcement Learning


Part 2: Modeling Uncertainty


Probability


Bayes Nets


Part 3: Learning from labeled Data


Classification


Part 4: Sub
-
Areas of AI


NLP


Vision


Philosophy of the class


Our goal is to use machines to solve hard problems that
traditionally would have been thought to require human
intelligence


We will try to follow a sound scientific/engineering
methodology


Consider relatively limited application domains


Use well
-
defined input/output specifications


Zero in on essential problem features


Focus on principles and basic building blocks

For next week


Check out the class website
http://www.tamaraberg.com/teaching/Spring_14/



Get the book. Do the readings.



Do a python tutorial. TAs will hold an in person
drop
-
in tutorial. Dates/times will be posted to the
class website (probably
Mon&Tues

evening).