500 MB Nyheder Direkte fra Internet 2/500 MB nyheder direkte fra internet CD 2.iso/start/data/text/ai.txt

Text File | 1994-09-21 | 61KB | 1,183 lines

      NATURAL VERSUS ARTIFICIAL
  You have what's called natural intelligence (except when your
friends accuse you of having ``natural stupidity''). The
intelligence of a computer, by contrast, is artificial. Can the
computer's artificial intelligence ever match yours?
  For example, can the computer ever develop the ``common sense''
needed to handle exceptions, such as a broken traffic light?
After waiting at a red light for several hours, the typical human
would realize the light was broken. The human would try to
proceed past the intersection, cautiously. Would a computer
programmed to ``never go on red'' be that smart?
  Researchers who study the field of artificial intelligence have
invented robots and many other fascinating computerized devices.
They've also been trying to develop computers that can understand
ordinary English commands and questions, so you won't have to
learn a ``programming language''. They've been trying to develop
expert systems ___ computers that imitate human experts such as
doctors and lawyers.

           EARLY DREAMERS
                                         The dream of making a
computer imitate us began many centuries ago. . . .

                                                    The Greeks
                                         The hope of making an
inanimate object act like a person can be traced back to the
ancient Greeks. According to Greek mythology, Pygmalion sculpted
a statue of a woman, fell in love with it, and prayed to the gods
to make it come to life. His wish was granted ___ she came to
life. And they lived happily ever after.

                                              Ramon Lull (1272 A.D.)
                                         In 1272 A.D. on the
Spanish island of Majorca, Ramon Lull invented the idea of a
machine that would produce all knowledge, by putting together
words at random. He even tried to build it.
                                         Needless to say, he was
a bit of a nut. Here's a description of his personality (written
by Jerry Rosenberg, abridged):
                                         Ramon Lull married young
and fathered two children ___ which didn't stop him from his
courtier's adventures. He had an especially strong passion for
married women. One day as he was riding his horse down the center
of town, he saw a familiar woman entering church for a High Mass.
Undisturbed by this circumstance, he galloped his horse into the
cathedral and was quickly thrown out by the congregants. The lady
was so disturbed by his scene that she prepared a plan to end
Lull's pursuit once and for all. She invited him to her boudoir,
displayed the bosom that he had been praising in poems written
for her, and showed him a cancerous breast. ``See, Ramon,'' she
said, ``the foulness of this body that has won thy affection! How
much better hadst thou done to have set thy love on Jesus Christ,
of Whom thou mayest have a prize that is eternal!''
                                         In shame Lull withdrew
from court life. On four different occasions a vision of Christ
hanging on the Cross came to him, and in penitence Lull became a
dedicated Christian. His conversion was followed by a pathetic
impulse to try to convert the entire Moslem world to
Christianity. This obsession dominated the remainder of his life.
His ``Book of Contemplation'' was divided into 5 books in honor
of the 5 wounds of Christ. It contained 40 subdivisions ___ for
the 40 days that Christ spent in the wilderness; 366 chapters ___
one to be read each day and the last chapter to be read only in a
leap year. Each of the chapters had 10 paragraphs to commemorate
the 10 commandments; each paragraph had 3 parts to signify the
trinity ___ for a total of 30 parts a chapter, signifying the 30
pieces of silver.
                                         In the final chapter of
his book he tried to prove to infidels that Christianity was the
only true faith.

  Gulliver's Travels Several centuries later ___ in 1726 ___
Lull's machine was pooh-poohed by Jonathan Swift, in Gulliver's
Travels.
  Gulliver meets a professor who has built such a machine. The
professor claims his machine lets ``the most ignorant person . .
. write books in philosophy, poetry, politics, law, mathematics,
and theology without the least assistance from genius and
study.''
  The machine is huge ___ 20 feet on each side ___ and contains
all the words of the language, in all their declensions, written
on scraps of paper that are glued onto bits of wood connected by
wires.
  Each of the professor's 40 students operates one of the
machine's 40 cranks. At a given signal, every student turns his
crank a random distance, to push the words into new positions.
  Gulliver says:
He then commanded 36 of the lads to read the several lines softly
as they appeared upon the frame; and where they found three or
four words together that might make part of a sentence, they
dictated to the four remaining boys who were scribes. Six hours a
day the young students were employed in this labor, and the
professor showed me several volumes in large folio already
collected, of broken sentences, which he intended to piece
together, and out of those rich materials to give the world a
complete body of all arts and sciences.

         Karel Capek (1920)
  The word robot was invented in 1920 by Karel Capek, a Czech
playwright. His play ``R.U.R.'' shows a factory where the workers
look human but are really machines. The workers are dubbed
robots, because the Czech word for slave is robotnik.
  His play is pessimistic. The invention of robots causes
unemployment. Men lose all ambition ___ even the ambition to
raise children. The robots are used in war, go mad, revolt
against mankind and destroy it. In the end only two robots are
left. It's up to them to repopulate the world.

         Isaac Asimov (1942)
  Many sci-fi writers copied Capek's idea of robots, with even
more pessimism. An exception was Isaac Asimov, who depicted
robots as being loving. He coined the word robotics, which means
the study of robots, and in 1942 developed what he calls the
``Three Laws of Robotics''. Here's the version he published in
1950:
  1. A robot may not injure a human being or, through inaction,
allow a human being to come to harm.
  2. A robot must obey the orders given it by human beings,
except where such orders would conflict with the First Law.
  3. A robot must protect its own existence, as long as such
protection does not conflict with either the First or the Second
Law.
                                               Norbert Wiener (1947)
                                         The word cybernetics was
invented in 1947 by Norbert Wiener, an MIT professor. He defined
it to be ``the science of control and communication in the animal
and the machine.'' Wiener and his disciples, who called
themselves cyberneticists, wondered whether it would be possible
to make an electrical imitation of the human nervous system. It
would be a ``thinking machine''. They created the concept of
feedback: animals and machines both need to perceive the
consequences of their actions, to learn how to improve
themselves. For example, a machine that is producing parts in a
factory should examine the parts it has produced, the heat it has
generated, and other factors, to adjust itself accordingly.
                                         Wiener, like Ramon Lull,
was something strange. He graduated from Tufts College when he
was 14 years old, got his doctorate from Harvard when he was 18,
and became the typical ``absent-minded professor''. Many
anecdotes are told about him.
                                         For example, once he
went to a conference and parked his car in the parking lot. When
the conference was over, he went to the lot, but forgot where he
parked his car, and even forgot what it looked like. So he waited
until all the other cars were driven away, and took the car that
was left.
                                         When he and his family
moved to a new house a few blocks away, his wife gave him written
directions on how to reach it, because she knew he was very
absent-minded. But sure enough, when he was leaving his office at
the end of the day, he couldn't remember where he put her note,
and of course he couldn't remember where the new house was. So he
drove to his old neighborhood instead. He saw a young child and
asked her, ``Little girl, can you tell me where the Wieners have
moved?'' ``Yes, Daddy,'' came the reply, ``Mommy said you'd
probably be here, so she sent me to show you the way home.''
                                         One day he was sitting
in the campus lounge, intensely studying a paper on the table.
Every now and then, he would get up, pace a bit, and then return
to the paper. Everyone was impressed by the enormous mental
effort reflected on his face. Once again he rose from his paper,
took a few rapid steps around the room, and collided with a
student. The student said, ``Good afternoon, Professor Wiener.''
Wiener stopped, stared, clapped a hand to his forehead, said
``Wiener ___ that's the word,'' and ran back to the table to fill
the word ``wiener'' in the crossword puzzle he was working on.
                                         Once he drove 150 miles
to a math conference at Yale University; but when the conference
was over, he forgot he had come by car, so he returned by bus.
The next morning, he went out to his garage to get his car,
discovered it was missing, and complained to the police that
while he was away someone had stolen it.
                                         Those anecdotes were
collected by Howard Eves, a math historian.

                                                Alan Turing (1950)
                                         Can a computer
``think''? In 1950, Alan Turing proposed the following test. In
one room, put a human and a computer. In another room, put
another human (called the Interrogator) and give him two
terminals ___ one for communication with the computer, and the
other for communication with the other human ___ but don't tell
the Interrogator which terminal is which. If he can't tell the
difference, the computer's doing a good job of imitating the
human, and, according to Turing, we should say that the computer
can ``think''.
  It's called the Imitation Game. The Interrogator asks
questions. The human witness answers honestly. The computer
pretends to be human.
  To win, the computer must be able to imitate human weaknesses
as well as strengths. For example, when asking to add two
numbers, it should pause before answering, as a human would. When
asked to write a sonnet, a good imitation-human answer would be,
``Count me out on this one. I never could write poetry.'' When
asked ``Are you human'', the computer should say ``yes''.
  Such responses wouldn't be hard to program. But a clever
Interrogator could give the computer a rough time, by requiring
it to analyze its own thinking:
Interrogator:In the first line of your sonnet which reads ``Shall
        I compare thee to a summer's day,'' wouldn't ``a spring
        day'' do as well or better?
Witness:It wouldn't scan.

Interrogator:How about ``a winter's day''. That would scan all
right.
Witness:Yes, but nobody wants to be compared to a winter's day.

Interrogator:Would you say Mr. Pickwick reminded you of
Christmas?
Witness:In a way.

Interrogator:Yet Christmas is a winter's day, and I don't think
        Mr. Pickwick would mind the comparison.
Witness:I don't think you're serious. By a winter's day one means
        a typical winter's day, rather than a special one like
        Christmas.
If the computer could answer questions that well, the
Interrogator would have a hard time telling it wasn't human.
  Donald Fink has suggested that the Interrogator say, ``Suggest
an unsolved problem and some methods for working toward its
solution,'' and ``What methods would most likely prove fruitful
in solving the following problem. . . . ''
  Turing believed computers would someday be able to win the game
and therefore be considered to ``think''. In his article, he
listed nine possible objections to his belief, and rebutted them.
. . .
  1. Soul Thinking's a function of man's immortal soul. Since
computers don't have souls, computers can't think.
  Rebuttal: since God's all-powerful, He can give computers souls
if He wishes. Just as we create children to house His souls, so
should we serve Him by creating computers.
  2. Dreadful If machines could equal us in thinking, that would
be dreadful!
  Rebuttal: too bad!
  3. Logicians Logicians have proved it's impossible to build a
computer that can answer every question.
  Rebuttal: is it possible to find a human that can answer every
question? Computers are no dumber than we. And though no one can
answer every question, why not build a succession of computers,
each one more powerful than the next, so every question could be
answered by at least one of them?
  4. Conscious Although computers can produce, they can't be
conscious of what they've produced. They can't feel pleasure at
their successes, misery at their mistakes, and depression when
they don't get what they want.
  Rebuttal: the only way to be absolutely sure whether a computer
has feelings is to become one. A more practical experiment would
be to build a computer that explains step-by-step its reasoning,
its motivations, and the obstacles it is trying to overcome, and
also analyzes emotional passages such as poetry. Such a computer
is clearly not just parroting.
                                         5. Human A computer
can't be kind, resourceful, beautiful, friendly, have initiative,
have a sense of humor, tell right from wrong, make mistakes, fall
in love, enjoy strawberries and cream, make someone fall in love
with it, learn from experience, use words properly, be the
subject of its own thought, have as much diversity of behavior as
a man, or do something really new.
                                         Rebuttal: why not?
Although such a computer hasn't been built yet, it might be
possible in the future.
                                         6. Surprise The computer
never does anything original or surprising. It does only what
it's told.
                                         Rebuttal: how do you
know ``original'' human work isn't just grown from a seed
implanted by teaching, or the effect of well-known general
principles? And who says computers aren't surprising? The
computer's correct answers are often surprisingly different from
a human's rough guesses.
                                         7. Binary Nerve cells
can sense gradual increases in electrical activity ___ you can
feel a ``little tingle'' or a ``mild pain'' or an ``ouch'' ___
whereas a computer's logic is only binary ___ either a ``yes'' or
``no''.
                                         Rebuttal: by using
techniques such as ``random numbers'', you can make the computer
imitate the flexible, probabilistic behavior of the nervous
system well enough so that the Interrogator can't tell the
difference.
                                         8. Rules Life can't be
reduced to rules. For example, if you have a traffic-light rule
that says ``stop when the light is red, and go when the light is
green'', what do you do when the light is broken, and both the
red and green appear simultaneously? Maybe you should have an
extra rule saying in that case to stop. But some further
difficulty may arise with that rule, and you'd have to create
another rule. And so on. You can't invent enough rules to handle
all cases. Since computers must be fed rules, they cannot handle
all of life.
                                         Rebuttal: although
life's more than a simple set of rules, it might be the
consequences of simple psychological laws of behavior, which the
computer could be taught.
                                         9. ESP Humans have
extrasensory perception (ESP), and computers don't.
                                         Rebuttal: maybe the
computer's random-number generator could be hooked up to be
affected by ESP. Or to prevent ESP from affecting the Imitation
Game, put both the human witness and the computer in a
telepathy-proof room.
                                         How to begin To make the
computer an intelligent creature, Turing suggested two possible
ways to begin. One way would be to teach the computer abstract
skills, such as chess. The other way would be to give the
computer eyes, ears, and other sense organs, teach it how to
speak English, and then educate it the same way you'd educate a
somewhat handicapped child.
                                         Suicide? Four years
later ___ on June 8, 1954 ___ Turing was found dead in bed.
According to the police, he died from potassium cyanide,
self-administered. He'd been plating spoons with potassium
cyanide in electrolysis experiments. His mother refuses to
believe it was suicide, and hopes it was just an accident.

         UNDERSTAND ENGLISH
  It's hard to make the computer understand plain English!

              Confusion
  For example, suppose you feed the computer this famous saying:
Time flies like an arrow.
What does that saying mean? The computer might interpret it three
ways. . . .
Interpretation 1: the computer thinks ``time'' is a noun, so the
sentence means ``The time can fly by as quickly as an arrow
flies.''

Interpretation 2: the computer thinks ``time'' is a verb, so the
sentence means ``Time the speed of flies like you'd time the
speed of an arrow.''

Interpretation 3: the computer thinks ``time'' is an adjective,
so the sentence means ``There's a special kind of insect, called
a `time fly', and those flies are attracted to an arrow (in the
same way moths are attracted to a flame).''
  Suppose a guy sits on a barstool and shares his drinks with a
tall woman while they play poker for cash. If the woman says to
him, ``Up yours!'', the computer might interpret it eight ways:
The woman is upset at what the man did.
The woman wants the man to raise up his glass, for a toast.
The woman wants the man to up the ante and raise his bet.
The woman wants the man to hold his cards higher, so she doesn't
see them.
The woman wants the man to pick up the card she dealt him.
The woman wants the man to raise his stool, so she can see him
eye-to-eye.
The woman wants the man to pull up his pants.
The woman wants the man to have an erection.
  For another example, suppose Mae West were to meet a
human-looking robot and ask him:
Is that a pistol in your pocket, or are you glad to see me?
The robot would probably analyze that sentence too logically,
then reply naively:
There is no pistol in my pocket, and I am glad to see you.
  In spite of those confusions, programmers have tried to make
the computer understand English. Here are some famous attempts. .
. .

           Baseball (1961)
  In 1961 at MIT, programmers made the computer answer questions
about baseball.
  In the computer's memory, they stored the month, day, place,
teams, and scores of each game in the American League for one
year. They programmed the computer so that you can type your
question in ordinary English. The computer analyzes your
question's grammar and prints the correct answer.
  Here are examples of questions the computer can analyze and
answer correctly:
Who did the Red Sox lose to on July 5?
Who beat the Yankees on July 4?
How many games did the Yankees play in July?
Where did each team play in July?
In how many places did each team play in July?
Did every team play at least once in each park in each month?

                                         To get an answer, the
computer turns your questions into equations:
Question
Equations
Where did the Red Sox play on July 7?
place = ?
                                                               te
am = Red Sox
                                                               mo
nth = July
                                                               da
y = 7

What teams won 10 games in July?
team (winning) = ?
                                                               ga
me (number of) = 10
                                                               mo
nth = July

On how many days in July did eight teams play?
day (number of) = ?
                                                               mo
nth = July
                                                               te
am (number of) = 8
                                         To do that, the computer
uses this table:
Word in your question                                  Equation
where                                                  place = ?
Red Sox                                                team = Red
Sox
July                                                   month =
July
who                                                    team = ?
team                                                   team =
                                         The computer ignores
words such as the, did, and play.
                                         If your question
mentions Boston, you might mean either ``place = Boston'' or
``team = Red Sox''. The computer analyzes your question to
determine which equation to form.
                                         After forming the
equations, the computer hunts through its memory, to find the
games that solve the equations. If an equation says ``number
of'', the computer counts. If an equation says ``winning'', the
computer compares the scores of opposing teams.
                                         The programmers were
Bert Green, Alice Wolf, Carol Chomsky, and Kenneth Laughery.

                                              What's a story problem?
                                         When you were in school,
your teacher told you a story that ended with a mathematical
question. For example:
Dick had 5 apples. He ate 3. How many are left?
                                         In that problem, the
last word is: left. That means: subtract. So the correct answer
is 5 minus 3, which is 2.
                                         Can the computer solve
problems like that? Here's the most famous attempt. . . .
           Arithmetic & algebra (1964)
  MIT awarded a Ph.D. to Daniel Bobrow, for programming the
computer to solve story problems involving arithmetic and
algebra.
  Customers Let's see how the computer solves this problem:
If the number of customers Tom gets is twice the square of 20
percent of the number of advertisements he runs, and the number
of advertisements he runs is 45, what is the number of customers
Tom gets?
  To begin, the computer replaces twice by 2 times, and replaces
square of by square.
  Then the computer separates the sentence into smaller
sentences:
The number of customers Tom gets is 2 times the square 20 percent
of the number of advertisements he runs. The number of
advertisements he runs is 45. What is the number of customers Tom
gets?
  The computer turns each sentence into an equation:
number of customers Tom gets = 2 * (.20 * number of
advertisements he runs)^2
number of advertisements he runs = 45
X = number of customers Tom gets
  The computer solves the equations and prints the answer as a
complete sentence:
The number of customers Tom gets is 162.
  Here's a harder problem:
The sum of Lois's share of some money and Bob's share is $4.50.
Lois's share is twice Bob's. Find Bob's and Lois's share.
  Applying the same method, the computer turns the problem into
these equations:
Lois's share of some money + Bob's share = 4.50 dollars
Lois's share = 2 * Bob's
X = Bob's
Y = Lois's share
  The computer tries to solve the equations but fails. So it
assumes ``Lois's share'' is the same as ``Lois's share of some
money'', and ``Bob's'' is the same as ``Bob's share''. Now it has
six equations:
Original equations
Lois's share of some money + Bob's share = 4.50 dollars
Lois's share = 2 * Bob's
X = Bob's
Y = Lois's share

Assumptions
Lois's share = Lois's share of some money
Bob's = Bob's share
  It solves them and prints:
Bob's is 1.50 dollars.
Lois's share is 3 dollars.
  Distance The computer can solve problems about distance:
The distance from New York to Los Angeles is 3000 miles. If the
average speed of a jet plane is 600 miles per hour, find the time
it takes to travel from New York to Los Angeles by jet.
  The resulting equations are:
distance from New York to Los Angeles = 3000 * miles
average speed of jet plane = (600 * miles)/(1 * hours)
X = time it takes to travel from New York to Los Angeles by jet
  The computer is unable to solve them. But in its memory it
finds the formula ``distance = speed * time''. It winds up with 7
equations:
Original equations
distance from New York to Los Angeles = 3000 * miles
average speed of jet plane = (600 * miles)/(1 * hours)
X = time it takes to travel from New York to Los Angeles by jet

Formula
distance = speed * time

Assumptions
distance = distance from New York to Los Angeles
speed = average speed of jet plane
time = time it takes to travel from New York to Los Angeles by
jet
  It solves them and prints:
The time it takes to travel from New York to Los Angeles by jet
is 5 hours.
                                                     Age The
computer can solve problems about age:
Mary is twice as old as Ann was when Mary was as old as Ann is
now. If Mary is 24 years old, how old is Ann?
                                                     To begin,
the computer replaces twice by 2 times, and replaces how old by
what.
                                                     When the
computer sees the words as old as, it knows the problem has to do
with ages, so it breaks the problem into these sentences:
Mary's age is 2 times Ann's age X years ago. X years ago Mary's
age is Ann's age now. Mary's age is 24. What is Ann's age?
The resulting equations are:
Mary's age = 2 * (Ann's age - X)
Mary's age - X = Ann's age
Mary's age = 24
Y = Ann's age
                                                     The computer
prints:
Ann's age is 18.
                                                     Hint If a
situation appears hopeless, the computer asks you for help. In
the following conversation, the human poses a problem, and the
computer begs for a hint:
Human:                                                   The
                                                         gross
                                                         weight
                                                         of a
                                                         ship is
                                                         20000
                                                         tons. If
                                                         its net
                                                         weight
                                                         is 15000
                                                         tons,
                                                         what is
                                                         the
                                                         weight
                                                         of the
                                                         ship's
                                                         cargo?
Computer:                                                Do you
                                                         know any
                                                         more
                                                         relation
                                                         ships
                                                         among
                                                         these
                                                         variable
                                                         s: gross
                                                         weight
                                                         of ship,
                                                         tons,
                                                         its net
                                                         weight,
                                                         weight
                                                         of
                                                         ship's
                                                         cargo?

Human:                                                   Yes.
Computer:                                                Tell me.

Human:                                                   The
                                                         weight
                                                         of a
                                                         ship's
                                                         cargo is
                                                         the
                                                         differen
                                                         ce
                                                         between
                                                         the
                                                         gross
                                                         weight
                                                         and the
                                                         net
                                                         weight.
Computer:                                                The
                                                         weight
                                                         of the
                                                         ship's
                                                         cargo is
                                                         5000
                                                         tons.
                                                     Limitations
The program has some limitations. It cannot solve quadratic
equations. If the computer tries to apply the formula ``distance
= speed * time'' to a problem involving two distances, it forgets
which distance is which.
                                                     The
computer's vocabulary is limited. It doesn't realize that how
many means what is the number of, and how far is means what is
the distance to. For problems about age, the characters must be
named Mary, Ann, Bill, Father, or Uncle, unless you diddle with
the computer's memory.
                                                     If the human
types Tom has 2 apples, 3 bananas, and 4 pears, the comma before
the and makes the computer split the sentence into two wrong
``sentences'':
Tom has 2 apples, 3 bananas.
4 pears.

  If the human mentions the number of times John went to the
movies, the computer thinks times means multiplication, and tries
to multiply number of by John went to the movies.

      Enclyclopedia (1964-1966)
  In 1964, Simmons, Klein, and McConlogue (at the Systems
Development Corporation) fed a child's encyclopedia into a
computer.
  If you type What do worms eat? the computer hunts through the
encyclopedia, to find sentences mentioning both worms and eat.
(To hasten the hunt, it uses an index produced by another
program.) It finds two sentences:
Birds eat worms on the grass.
Most worms usually eat grass.
  After analyzing the grammar of your question and those
sentences, the computer realizes the first sentence is
irrelevant, and prints just the correct answer:
Most worms usually eat grass.
  In 1965, the program's abilities were extended, so that if you
type What animals live longer than men? the computer searches
through the encyclopedia for related words:
Word in sentenceRelated words searched
animals     mammals, reptiles, fish
live        age
longer      older, ancient
men         person, people, women
  Here's an example of the program's operation in 1966. The human
creates some encyclopedia material about horses, and then
retrieves it:
Human:Enter horse=noun, is=isverb, animal=noun, live=verb,
      on=prep, farm=noun, strong=adj, pull=verb, wagon=noun,
      most=adj, are=isverb, eat=verb, hay=noun, all=adj, red=adj,
      many=adj, have=haveverb, long=adj, mane=noun, some=adj,
      person=noun, race=verb.
Computer:Entered in dictionary.

Human:Plurals horse=horses, animal=animals, farm=farms,
      wagon=wagons, mane=manes, person=people.
Computer:Ok.

Human:Start.
Computer:Ready.

Human:A horse is an animal. Horses live on a farm. Strong horses
      pull wagons. Most horses are strong. Horses eat hay. All
      horses are red. Many horses have long manes. Some people
      race horses.
Computer:Learned.

Human:Forget ``all horses are red''.
Computer:Forgotten.

Human:What is a horse?
Computer:Horse is an animal.

Human:What do horses eat?
Computer:Horses eat hay.

Human:What do horses do?
Computer:Horses live on a farm and eat hay. Strong horses pull
wagons.

Human:What do strong horses do?
Computer:Strong horses pull wagons.

Human:Do many horses have long manes?
Computer:Yes.

Human:Do all horses have long manes?
Computer:To my knowledge, no.

Human:Describe horses?
Computer:Horses are an animal. Most horses are strong. Many
      horses have long manes. Horses live on a farm and eat hay.
      Strong horses pull wagons. Some people race horses.

                                         When the computer's
answer consists of several sentences, it prints the most relevant
sentence first, and the others in decreasing order of relevance.

                                                  Military (1966)
                                         Thompson and Craig (at
General Electric) made the computer answer military questions
such as:
Has the 25th battalion arrived in Texas since 3 P.M.?

Is the 100th scheduled to arrive at Ft. Lewis before the 200th
leaves Ft. Lewis?

                                                 Eliza (1966-1967)
                                         In 1966 at MIT, Joseph
Weizenbaum wrote the Eliza program, which makes the computer act
as a psychotherapist.
                                         In 1967, he changed the
program, to make it handle keywords such as also, call, compute,
define, is, let, of, thanks, where, and the symbol =.
                                         In the following
conversation, the human teaches the computer how to find the area
of a circle, a sphere, and a square, and then asks the computer
questions about geometry. The human also teaches the computer how
to speak German ___
English                                      German
I say                                        ich sage
I mean                                       meine ich
what is                                      wieviel ist
squared                                      quadrat
and gradually starts speaking to the computer in German.
Human:                                       The area of a circle
                                             is pi times the
                                             radius of the circle
                                             squared. The area of
                                             a sphere is pi times
                                             the diameter of the
                                             sphere squared. The
                                             area of a square is
                                             the side of the
                                             square squared. The
                                             diameter of an
                                             object is twice the
                                             radius of the
                                             object. The radius
                                             of a ball is 10.
                                             What is the area of
                                             the ball?
Computer:                                    The assumption that
                                             ball is circle is
                                             consistent ___ shall
                                             I go on?

Human:                                       No.
Computer:                                    The assumption that
                                             ball is sphere and
                                             object is consistent
                                             ___ shall I go on?

Human:                                       Yes.
Computer:                                    It's 1256.6359.

Human:                                       What is the diameter
of the ball?
Computer:                                    It's 20.

Human:                                       The radius of a dish
is 10. What's the area of the dish?
Computer:                                    The assumption that
dish is circle is consistent ___ shall I go on?

Human:                                       Yes.
Computer:                                    It's 314.15899.

Human:                                       The radius of a
                                             globe is 10. A globe
                                             is a sphere. A
                                             sphere is an object.
                                             What is the area of
                                             the globe?
Computer:                                    It's 1256.6359.

Human:                                       The side of a plate
is 10. What is the area of the plate?
Computer:                                    The assumption that
                                             plate is square is
                                             consistent ___ shall
                                             I go on?

Human:                                       Yes.
Computer:                                    It's 100.

Human:                                       When I say board I
                                             mean plate. What is
                                             3 times the side of
                                             the board?
Computer:                                    It's 30.

Human:                                       Please call that x.
Let f(z) be z squared minus z. Compute f(x).
Computer:                                    It's 870.

Human:                                       When I say ich sage
                                             I mean I say. When
                                             ich sage meine ich I
                                             mean I mean. Wenn
                                             ich sage wieviel ist
                                             meine ich what is.
                                             Wenn ich sage
                                             quadrat meine ich
                                             squared. Nun, sagen
                                             sie mir bitte,
                                             wieviel is x
                                             quadrat.
Computer:                                    I didn't understand
you.

Human:                                       Ja, tut mir leid,
ich sollte fragen wieviel IST x quadrat.
Computer:                                    It's 900.

           Calculus (1969)
  At MIT, Charniak made the computer solve story problems
involving calculus.
Human:Water is flowing into a conical filter at the rate of 15
      cubic inches per second. If the radius of the base of the
      filter is 5 inches and the altitude is 10 inches, find the
      rate at which the water level is rising when the volume is
      100 cubic inches.
Computer:The answer is .53132943 * in * sec^-1 * pi^-.33333332.

         Probability (1971)
  Rensselaer Polytechnic Institute awarded a Ph.D. to J.P. Gelb,
for making the computer solve story problems involving
probability.
Human:From a zorch containing 4 ferd and 3 brakky and 5
      chartreuse werfels, 3 are drawn. What is the probability
      that 2 are chartreuse and the other brakky?
Computer:Replacement involved?

Human:No.
Computer:3/22 (or .1363636).


         SURVEYING THE FIELD
                                         The field of
``artificial intelligence'' includes many categories.
                                         For example, it includes
attempts to make the computer win at chess and checkers,
understand English, and create its own original art and music. It
also includes attempts to imitate human feelings, personal
interactions, and therapists. I explained those topics earlier.

                                                  Protocol method
                                         During the 1950's and
1960's, most research in artificial intelligence was done at the
Massachusetts Institute of Technology (MIT) and the Carnegie
Institute of Technology (CIT, now called Carnegie-Mellon
University). At Carnegie, the big names were Allen Newell and
Herbert Simon. They invented the protocol method. In the protocol
method, a human is told to solve a tough problem and, while he's
solving it, to say at each moment what he's thinking. A
transcript of his train of thought is recorded and called the
protocol. Then programmers try to make the computer imitate that
train of thought.
                                         Using the protocol
method, Newell and Simon produced programs that could ``think
like humans''. The thinking, like human thinking, was imperfect.
Their research did not try to make the computer a perfect
thinker; instead, it tried to gain insight into how humans think.
Their point of view was: if you think you really understand human
psychology, go try to program it. Their attempt to reduce human
psychology to computer programs is called mentalism, and has
replaced Skinner's stimulus-response behaviorism as the dominant
force in psychology today.

                                                   Abstract math
                                         Many programmers have
tried to make the computer do abstract math.
                                         In 1957 Newell, Simon,
and Shaw used the protocol method to make the computer prove
theorems about symbolic logic, such as ``Not (p or q) implies not
p''. In 1959 and 1960, Herbert Gelernter and his friends made the
computer prove theorems about Euclidean geometry, such as ``If
the segment joining the midpoints of the diagonals of a trapezoid
is extended to intersect a side of the trapezoid, it bisects that
side.''
                                         In 1961, MIT awarded a
Ph.D. to James Slagle for making the computer compute indefinite
integrals, such as:
       4
⌠     x
            dx
⌡     2 5/2
  (1-x )
The computer gets the answer, which is:
              3
           tan  arcsin x
arcsin x +               - tan arcsin x + c
                 3
                                         Each of those programs
works by drawing a tree inside the computer's memory. Each branch
of the tree represents a possible line of attack. The computer
considers each branch and chooses the one that looks most
promising.
                                         A better symbolic-logic
program was written by Hao Wang in 1960. His program doesn't need
trees; it always picks the right attack immediately. It's
guaranteed to prove any theorem you hand it, whereas the program
by Newell, Simon, and Shaw got stuck on some hard ones.
  A better indefinite integration program was written by Joel
Moses in 1967 and further improved in 1969. It uses trees very
rarely, and solves almost any integration problem.
  A program that usually finds the right answer but might fail on
hard problems is called heuristic. A heuristic program usually
involves trees. The checkers, chess, and geometry programs are
heuristic. A program that's guaranteed to always give the correct
answer is called algorithmic. The original symbolic-logic program
was heuristic, but Wang's improvement is algorithmic; Moses's
indefinite integration program is almost algorithmic.

                       GPS
  In 1957 Newell, Simon, and Shaw began writing a single program
to solve all problems. They called the program GPS (General
Problem Solver). If you feed the program a goal, a list of
operators, and associated information, the program will tell you
how to achieve the goal by using the operators.
  For example, suppose you want the computer to solve this simple
problem: a monkey would like to eat some bananas that are too
high for him to reach, but there's a box nearby he can stand on.
How can he get the bananas?
  Feed the GPS program this information. . . .
Now:  monkey's place = place#1; box's place = place#2; contents
of monkey's hand = empty

Want: contents of monkey's hand = the bananas

Difficulties:contents of monkey's hand is harder to change than
      box's place, which is harder to change than monkey's place

Allowable operatorDefinition
climb box     before:monkey's place = box's place
              after:monkey's place = on the box

walk to x     after:monkey's place = x

move box to x before:monkey's place = box's place
              after:monkey's place = x; box's place = x

get bananas   before:box's place = under the bananas; monkey's
place = on the box
              after:contents of monkey's hand = the bananas
  GPS will print the solution:
walk to place#2
move box to under the bananas
climb box
get bananas
  The GPS approach to solving problems is called means-ends
analysis: you tell the program the means (operators) and the end
(goal). The program has proved theorems in symbolic logic,
computed indefinite integrals, and solved many famous puzzles,
such as ``The Missionaries and the Cannibals'', ``The Tower of
Hanoi'', and ``The 5-Gallon Jug and the 8-Gallon Jug''. But the
program works slowly, and you must feed it lots of information
about the problem. The project was abandoned in 1967.

                     Vision
  Another large topic in artificial intelligence is computer
vision: making the computer see.
  The first problem tackled was pattern recognition: making the
computer read handwritten printed letters. The problem is hard,
because some people make their letters very tall or wide or
slanted or curled or close together, and the pen may skip.
Reasonably successful programs were written, although computers
still can't tackle script.
  Interest later shifted to picture processing: given a
photograph of an object, make the computer tell what the object
is. The problem is hard, because the photo may be taken from an
unusual angle and be blurred, and because the computer gets
confused by shadows.
  Scene analysis is even harder: given a picture of a group of
objects, make the computer tell which object is which. The
problem is hard, because some of the objects may be partly hidden
behind others, and because a line can have two different
interpretations: it can be a crease in one object, or a
dividing-line between two objects.
  Most of the research in picture processing and scene analysis
was done from 1968 to 1972.
                                                     Ray Kurzweil
has invented an amazing machine whose camera looks at a book and
reads the book, by using a voice synthesizer. Many blind people
use it.

                                                            Robots
                                                     Researchers
have built robots. The first robots were just for experimental
fun, but today's robots are truly useful: for example, the
Japanese are using robots to manufacture cars. In the United
States, many young kids are being taught ``LOGO'', which is a
language developed at the MIT Artificial Intelligence Laboratory
that makes the computer control a robot turtle.

                                                       Today's research
                                                     Today,
research in artificial intelligence is done at four major
universities: MIT, Carnegie, Stanford, and Edinburgh (Scotland).
          Reflexive control
  In the Soviet Union, weird researchers have studied reflexive
control: they programmed the computer to be disobedient. The
first such programmer was Lefevr, in 1967. In 1969 Baranov and
Trudolyubov extended his work, by making the computer win this
disobedience game:
The human begins by choosing either node 9 or node 26, but
doesn't tell the computer which node he's chosen. The computer
starts at node 12; on each turn, it moves to an adjacent node.
When it reaches either node 9 or node 26, the game ends: if the
node the computer reaches is one of the human chose, the human
wins; if the computer reaches the opposite node, the computer
wins. Before each move, the human tells the computer where to go;
but the computer may decide to do the opposite (disobey).
  What strategy should the computer use? If it always obeys, or
always disobeys the human will catch on and make it lose.
  Instead, Baranov and Trudolyubov programmed the computer to
react as follows:
obey the human twice, then disobey three times, then obey once,
disobey thrice, obey once, disobey twice, obey thrice, disobey
once, obey thrice, disobey once, . . .
The irregular alternation of obedience and disobedience confuses
the human in a way that works to the computer's advantage. Using
that strategy, the computer played against 61 humans, and won
against 44 of them (72%). In other words, the typical human tried
to mislead the computer but in fact ``clued it in'' to the
human's goal.
  Later experiments with other games indicated that the following
pattern of disobedience is usually more effective:
obey the human twice, disobey thrice, obey once, disobey four
times, obey once, disobey thrice, obey thrice, disobey twice,
obey thrice, disobey once, obey once, disobey once

                                                  Misinformation
                                         Unfortunately, most
research in the field of artificial intelligence is just a lot of
hot air. For years, researchers have been promising that
intelligent, easy-to-use English-speaking computers and robots
would be available at low prices ``any day now''. After several
decades of listening to such hoopla, I've given up waiting. The
field of artificial intelligence should be renamed ``artificial
optimism''.
                                         Whenever a researcher in
the field of artificial intelligence promises you something,
don't believe it until you see it and use it personally, so you
can evaluate its limitations.
                                         If a computer seems to
give intelligent replies to English questions posed by a salesman
or researcher demonstrating artificial intelligence, try to
interrupt the demo and ask the computer your English questions.
You'll typically find that the computer doesn't understand what
you're talking about at all: the demo was a cheap trick that
works just with the peculiar English questions asked by the
demonstrator.
                                         For many years, the top
researchers in artificial intelligence have been exaggerating
their achievements and underestimating how long it will take to
develop a truly intelligent computer. Let's look at their history
of lies. . . .
                                         In 1957 Herbert Simon
said, ``Within ten years a digital computer will be the world's
chess champion.'' In 1967, when the ten years had elapsed, the
only decent chess program was Greenblatt's, which the American
Chess Federation rated ``class D'' (which means ``poor''). Though
chess programs have improved since then, the best chess program
is still far less than an  ``international master'' or
``grandmaster'' or ``world champion''.
                                         In 1957 Simon also said,
``Within ten years a digital computer will discover and prove an
important new mathematical theorem.'' He was wrong. The computer
still hasn't discovered or proved any important new mathematical
theorem. The closest call came in 1976, when it did the
non-abstract part of the proof of the ``4-color theorem''.
                                         In 1958 Newell, Simon,
and Shaw wrote a chess-playing program which they admitted was
``not fully debugged'' so that one ``cannot say very much about
the behavior of the program''; but they claimed it was ``good in
spots (opening)''. In 1959 the founder of cybernetics, Norbert
Wiener, exaggerated about their program; he told New York
University's Institute of Philosophy that ``chess-playing
machines as of now will counter the moves of a master player with
the moves recognized as right in the textbooks, up to some point
in the middle game.'' In the same symposium Michael Scriven
carried the exaggeration even further by saying, ``Machines are
already capable of a good game.'' In fact, the program they were
describing played very poorly, and in its last official bout
(October 1960) was beaten by a ten-year-old kid who was a novice.
                                         In 1960 Herbert
Gelernter (who wrote the geometry-theorem program) said, ``Today
hardly an expert will contest the assertion that machines will be
proving interesting theorems in number theory three years
hence.'' More than twenty years have elapsed since then, but
neither Gelernter nor anyone else has programmed the computer to
prove theorems in number theory.
  In June 1963 this article appeared in the Chicago Tribune:
The development of a machine that can listen to any conversation
and type out the remarks just like an office secretary was
announced yesterday by a Cornell University expert on learning
machines. The device is expected to be in operation by fall.
Frank Rosenblatt, director of Cornell's cognitive systems
research, said the machine will be the largest ``thinking''
device built to date. Rosenblatt made his announcement at a
meeting on learning machines at Northwestern University's
Technological Institute.
No such machine exists today, let alone in 1963.
  Also in 1963, W. Ross Ashby said, ``Gelernter's theorem-proving
program has discovered a new proof of the pons asinorum that
demands no construction.'' He said the proof is one that ``the
greatest mathematicians of 2000 years have failed to notice . . .
which would have evoked the highest praise had it occurred.'' In
fact, the pons asinorum is just the simple theorem that the
opposite angles of an isosceles triangle are equal, and the
computer's constructionless proof had already been discovered by
Pappus in 300 A.D.
  In 1968 the head of artificial intelligence in Great Britain,
Donald Michie, said, ``Today machines can play chess at
championship level.'' In fact, when computers were allowed to
participate in human chess tournaments, they almost always lost.
  In 1970 the head of artificial intelligence at MIT, Marvin
Minsky, said:
In three to eight years we will have a machine with the general
intelligence of an average human being. I mean a machine that
will be able to read Shakespeare, grease a car, play office
politics, tell a joke, have a fight. At that point, the machine
will begin to educate itself with fantastic speed. In a few
months it will be at genius level, and a few months after that
its powers will be incalculable.
His prediction that it would happen in three to eight years ___
between 1973 and 1978 ___ was ridiculous. I doubt it will happen
during this century, if ever.
  Exaggerations concern not just the present and future but also
the past. Back in 1962 Arthur Samuel's checker program won one
game against Robert Nealey, ``a former Connecticut checkers
champion''. Notice that Nealey was a former champion, not the
current champion when the game was played. Also notice the
program won a single game, not a match; and in fact it lost to
Nealey later. In 1971 James Slagle slid over those niceties, when
he just said that the program ``once beat the champion of
Connecticut.'' More recent writers, reading Slagle's words, have
gone a step further and omitted the word once: one textbook says,
``The current program beat the champion of Connecticut''. It's
not true.
  Why do leaders of artificial intelligence consistently
exaggerate? The answer is obvious: to get more research funds
from the government. Hubert Dreyfus, chairman of the philosophy
department at Berkeley, annoys them by attacking their claims.
                                                     The brain
                                         Will the computer be
able to imitate the human brain? Opinions vary.
                                         Marvin Minsky, head of
artificial intelligence at MIT, says yes: ``After all, the human
brain is just a computer that happens to be made out of meat.''
                                         Biologists argue no: the
brain is composed of 12 billion neurons, each of which has
between 5,000 and 60,000 dendrites for input and a similar number
of axons for output; the neurons act in peculiar ways, and no
computer could imitate all that with complete accuracy ___ ``The
neuron is qualitatively quite different from on-off components of
current computers.''
                                         Herbert Simon (head of
artificial intelligence at Carnegie and a psychologist), points
out that certain aspects of the brain, such as short-term memory,
are known to have very limited capacity and ability. He believes
the inner workings of the brain are reasonably simple; it
produces complicated output only because it receives complicated
input from the sense organs and environment: ``A man, viewed as a
behaving system, is quite simple. The apparent complexity of his
behavior over time is largely a reflection of the complexity of
the environment in which he finds himself.'' Simon believes that
if a computer were given good sense organs, the ability to move,
and an elementary ability to learn, and were placed in a
stimulating environment (unlike the dull four walls of a computer
center), it would start acting in complex ways also.
                                         Hubert Dreyfus, chairman
of the philosophy department at Berkeley, argues that progress in
artificial intelligence has been very small, is being blocked now
by impenetrable barriers, and ___ most important ___ the
computer's approach to solving problems bears little relationship
to the more powerful methods used by humans. He's cynical about
the claim that an improvement in computer programs represents
progress toward understanding the human mind, which is altogether
different: ``According to this definition, the first man to climb
a tree could claim tangible progress toward reaching the moon.
Rather than climbing blindly, it's better to look where one is
going.''