Artificial intelligence
1 / 68

Artificial Intelligence - PowerPoint PPT Presentation

  • Updated On :

Artificial Intelligence. Our Working Definition of AI. Artificial intelligence is the study of how to make computers do things that people are better at or would be better at if: they could extend what they do to a World Wide Web-sized amount of data and not make mistakes. Why AI?.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

PowerPoint Slideshow about 'Artificial Intelligence' - andrew

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

Our working definition of ai l.jpg
Our Working Definition of AI

  • Artificial intelligence is the study of how to make computers do things that people are better at or would be better at if:

  • they could extend what they do to a World Wide

  • Web-sized amount of data and

  • not make mistakes.

Why ai l.jpg
Why AI?

"AI can have two purposes. One is to use the power of computers to augment human thinking, just as we use motors to augment human or horse power. Robotics and expert systems are major branches of that. The other is to use a computer's artificial intelligence to understand how humans think. In a humanoid way. If you test your programs not merely by what they can accomplish, but how they accomplish it, they you're really doing cognitive science; you're using AI to understand the human mind."

- Herb Simon

The dartmouth conference and the name artificial intelligence l.jpg
The Dartmouth Conference and the Name Artificial Intelligence

J. McCarthy, M. L. Minsky, N. Rochester, and C.E. Shannon. August 31, 1955. "We propose that a 2 month, 10 man study of artificial intelligence be carried out during the summer of 1956 at Dartmouth College in Hanover, New Hampshire. The study is to proceed on the basis of the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it."

Time line the big picture l.jpg
Time Line – The Big Picture Intelligence

academic $ academic and routine

50 60 70 80 90 00 10

1956 Dartmouth conference.

1981 Japanese Fifth Generation project launched as the

Expert Systems age blossoms in the US.

1988 AI revenues peak at $1 billion. AI Winter begins.

The origins of ai hype l.jpg
The Origins of AI Hype Intelligence

1950 Turing predicted that in about fifty years "an average interrogator will not have more than a 70 percent chance of making the right identification after five minutes of questioning".

1957 Newell and Simon predicted that "Within ten years a computer will be the world's chess champion, unless the rules bar it from competition."

Evolution of the main ideas l.jpg
Evolution of the Main Ideas Intelligence

  • Wings or not?

  • Games, mathematics, and other knowledge-poor tasks

  • The silver bullet?

  • Knowledge-based systems

  • Hand-coded knowledge vs. machine learning

  • Low-level (sensory and motor) processing and the resurgence of subsymbolic systems

  • Robotics

  • Natural language processing

Symbolic vs subsymbolic ai l.jpg
Symbolic vs. Subsymbolic AI Intelligence

Subsymbolic AI: Model intelligence at a level similar to the neuron. Let such things as knowledge and planning emerge.

Symbolic AI: Model such things as knowledge and planning in data structures that make sense to the programmers that build them.

(blueberry (isa fruit)

(shape round)

(color purple)

(size .4 inch))

The origins of subsymbolic ai l.jpg
The Origins of Subsymbolic AI Intelligence

1943 McCulloch and Pitts A Logical Calculus of the Ideas Immanent in Nervous Activity

“Because of the “all-or-none” character of nervous activity, neural events and the relations among them can be treated by means of propositional logic”

Interest in subsymbolic ai l.jpg
Interest in Subsymbolic AI Intelligence

40 50 60 70 80 90 00 10

The origins of symbolic ai l.jpg
The Origins of Symbolic AI Intelligence

  • Games

  • Theorem proving

Games l.jpg
Games Intelligence

  • 1950 Claude Shannon published a paper describing how

  • a computer could play chess.

  • 1952-1962 Art Samuel built the first checkers program

  • 1957 Newell and Simon predicted that a computer will

  • beat a human at chess within 10 years.

  • 1967 MacHack was good enough to achieve a class-C

  • rating in tournament chess.

  • 1994 Chinook became the world checkers champion

  • 1997 Deep Blue beat Kasparpov

  • 2007 Checkers is solved

  • Summary

Games13 l.jpg
Games Intelligence

  • AI in Role Playing Games – now we need knowledge

Logic theorist l.jpg
Logic Theorist Intelligence

  • Debuted at the 1956 summer Dartmouth conference, although it was hand-simulated then.

  • Probably the first implemented A.I. program.

  • LT did what mathematicians do: it proved theorems. It proved, for example, most of the theorems in Chapter 2 of Principia Mathematica [Whitehead and Russell 1910, 1912, 1913].

  • LT began with the five axioms given in Principia Mathematica. From there, it began to prove Principia’s theorems.

Logic theorist15 l.jpg
Logic Theorist Intelligence

  • LT used three rules of inference:

    • Substitution (which allows any expression to be substituted, consistently, for any variable):

      • From: A  B  A, conclude: fuzzy  cute  fuzzy

    • Replacement (which allows any logical connective to be replaced by its definition, and vice versa):

      • From A  B, conclude A  B

    • Detachment (which allows, if A and AB are theorems, to assert the new theorem B):

      • From man and man  mortal, conclude: mortal

Logic theorist16 l.jpg
Logic Theorist Intelligence

In about 12 minutes LT produced, for theorem 2.45:

(pq) p (Theorem 2.45, to be proved.)

1. A (AB) (Theorem 2.2.)

2. p (pq) (Subst. p for A, q for B in 1.)

3. (AB)  (BA) (Theorem 2.16.)

4. (p (pq))  ((pq) p) (Subst. p for A, (pq) for B in 3.)

5. (pq) p (Detach right side of 4, using 2.)

Q. E. D.

Logic theorist17 l.jpg
Logic Theorist Intelligence

The inference rules that LT used are not complete.

The proofs it produced are trivial by modern standards.

For example, given the axioms and the theorems prior to it, LT tried for 23 minutes but failed to prove theorem 2.31:

[p (qr)]  [(pq) r].

LT’s significance lies in the fact that it opened the door to the development of more powerful systems.

Mathematics l.jpg
Mathematics Intelligence

1956 Logic Theorist (the first running AI program?)

1961 SAINT solved calculus problems at the college

freshman level

1967 Macsyma

Gradually theorem proving has become well enough understood that it is usually no longer considered AI.

Discovery l.jpg
Discovery Intelligence

  • AM “discovered”:

    • Goldbach’s conjecture

    • Unique prime factorization theorem

What about things that people do easily l.jpg
What About Things that People Do IntelligenceEasily?

  • Common sense reasoning

  • Vision

  • Moving around

  • Language

What about things people do easily l.jpg
What About Things People Do IntelligenceEasily?

  • If you have a problem, think of a past situation where you solved a similar problem.

  • If you take an action, anticipate what might happen next.

  • If you fail at something, imagine how you might have done things differently.

  • If you observe an event, try to infer what prior event might have caused it.

  • If you see an object, wonder if anyone owns it.

  • If someone does something, ask yourself what the person's purpose was in doing that.

They require knowledge l.jpg
They Require Knowledge Intelligence

  • Why do we need it?

Find me stuff about dogs who save people’s lives.

  • How can we represent it and use it?

  • How can we acquire it?

Slide23 l.jpg
Why? Intelligence

  • Why do we need it?

Find me stuff about dogs who save people’s lives.

Two beagles spot a fire. Their barking alerts neighbors, who call 911.

  • How can we represent it and use it?

  • How can we acquire it?

Even children know a lot l.jpg
Even Children Know a Lot Intelligence

A story described in Charniak (1972):

Jane was invited to Jack’s birthday party. She wondered if he would like a kite. She went into her room and shook her piggy bank. It made no sound.

We divide things into concepts l.jpg
We Divide Things into Concepts Intelligence

  • What’s a party?

  • What’s a kite?

  • What’s a piggy bank?

What is a concept l.jpg
What is a Concept? Intelligence

Let’s start with an easy one: chair

Chair l.jpg
Chair? Intelligence

Chair28 l.jpg
Chair? Intelligence

Chair29 l.jpg
Chair? Intelligence

Chair30 l.jpg
Chair? Intelligence

Chair31 l.jpg
Chair? Intelligence

Chair32 l.jpg
Chair? Intelligence

Chair33 l.jpg
Chair? Intelligence

Chair34 l.jpg
Chair? Intelligence

Chair35 l.jpg
Chair? Intelligence

Chair36 l.jpg
Chair? Intelligence

Chair37 l.jpg
Chair? Intelligence

Chair38 l.jpg
Chair? Intelligence

Chair39 l.jpg
Chair? Intelligence

Chair40 l.jpg
Chair? Intelligence

Chair41 l.jpg
Chair? Intelligence

The bottom line?

How can we teach things to computers l.jpg
How Can We Teach Things to Computers? Intelligence

A quote from John McCarthy:

In order for a program to be capable of learning something, it must first be capable of being told it.

Do we believe this?

Some things are easy l.jpg
Some Things are Easy Intelligence

If dogs are mammals and mammals are animals, are dogs mammals?

Some things are harder l.jpg
Some Things Are Harder Intelligence

If most Canadians have brown eyes, and most brown eyed people have good eyesight, then do most Canadians have good eyesight?

Some things are harder45 l.jpg
Some Things Are Harder Intelligence

If most Canadians have brown eyes, and most brown eyed people have good eyesight, then do most Canadians have good eyesight?

Maybe not for at least two reasons:

It might be true that, while most brown eyed people have good eyesight, that’s not true of Canadians.

Suppose that 70% of Canadians have brown eyes and 70% of brown eyed people have good eyesight. Then assuming that brown-eyed Canadians have the same probability as other brown-eyed people of having good eyesight, only 49% of Canadians are brown eyed people with good eyesight.

Concept acquisition l.jpg
Concept Acquisition Intelligence

Pat Winston’s program (1970) learned concepts in the blocks micro-world.

Concept acquisition47 l.jpg
Concept Acquisition Intelligence

The arch concept:

Further complications from how language is used l.jpg
Further Complications from How Language is Used Intelligence

  • After the strike, the president sent them away.

  • After the strike, the umpire sent them away.

The word “strike” refers to two different concepts.

When other words in context aren t enough l.jpg
When Other Words in Context Aren’t Enough Intelligence

  • I need a new bonnet.

  • The senator moved to table the bill.

Compiling common sense knowledge l.jpg
Compiling Common Sense Knowledge Intelligence

  • CYC (

  • UT ( )

  • WordNet (

Distributed knowledge acquisition l.jpg
Distributed Knowledge Acquisition Intelligence

  • Acquiring knowledge for use by people

    • Oxford English Dictionary ( )

    • Wikipedia

  • Acquiring knowledge for use by programs

    • ESP (

    • Open Mind (

    • CYC (

Reasoning l.jpg
Reasoning Intelligence

We can describe reasoning as search in a space of possible situations.

Breadth first search l.jpg
Breadth-First Search Intelligence

Depth first search l.jpg
Depth-First Search Intelligence

The british museum algorithm l.jpg
The British Museum Algorithm Intelligence

A simple algorithm: Generate and test

When done systematically, it is basic depth-first search.

But suppose that each time we end a path, we start over at the top and choose the next path randomly. If we try this long enough, we may eventually hit a solution. We’ll call this

The British Museum Algorithm or

The Monkeys and Typewriters Algorithm

A version of depth first search branch and bound l.jpg
A Version of Depth-First Search: IntelligenceBranch and Bound

Consider the problem of planning a ski vacation.

Fly to A $600

Fly to B $800

Fly to C $2000

Stay D $200


Stay E $250


Total cost


Problem reduction l.jpg
Problem Reduction Intelligence

Goal: Acquire TV

Steal TV

Earn Money

Buy TV

Or another one: Theorem proving in which we reason backwards from the theorem we’re trying to prove.

Hill climbing l.jpg
Hill Climbing Intelligence

Problem: You have just arrived in Washington, D.C. You’re in your car, trying to get downtown to the Washington Monument.

Hill climbing is close good enough l.jpg
Hill Climbing – Is Close Good Enough? Intelligence



  • Is A good enough?

  • Choose winning lottery numbers

Hill climbing is close good enough61 l.jpg
Hill Climbing – Is Close Good Enough? Intelligence



  • Is A good enough?

  • Choose winning lottery numbers

  • Get the cheapest travel itinerary

  • Clean the house

Expert systems l.jpg
Expert Systems Intelligence

Expert knowledge in many domains can be captured as rules.

  • Dendral (1965 – 1975)

  • If: The spectrum for the molecule has two peaks at masses x1 and x2 such that:

    • x1 + x2 = molecular weight + 28,

    • x1 -28 is a high peak,

    • x2 – 28 is a high peak, and

    • at least one of x1 or x2 is high,

  • Then: the molecule contains a ketone group.

To interpret the rule l.jpg
To Interpret the Rule Intelligence

Mass spectometry

Ketone group:

Expert systems64 l.jpg
Expert Systems Intelligence

1975 Mycin attaches probability-like numbers to rules:

If: (1) the stain of the organism is gram-positive, and

(2) the morphology of the organism is coccus, and

(3) the growth conformation of the organism is clumps

Then: there is suggestive evidence (0.7) that the identity of the organism is stphylococcus.

Expert systems today medicine l.jpg
Expert Systems – Today: Medicine Intelligence

  • One example domain, medicine, has expert systems whose tasks include:

    • arrhythmia recognition from electrocardiograms

    • coronary heart disease risk group detection

    • monitoring the prescription of restricted use antibiotics

    • early melanoma diagnosis

    • gene expression data analysis of human lymphoma

    • breast cancer diagnosis

Expert systems today build your own l.jpg
Expert Systems – Today: Build Your Own Intelligence



(whales, graduate school)

Taking the ap chemistry exam l.jpg
Taking the AP Chemistry Exam Intelligence

QUESTION: Sodium azide is used in air bags to rapidly produce gas to inflate the bag. The products of the decomposition reaction are:(a) Na and water.(b) Ammonia and sodium metal.(c) N2 and O2(d) Sodium and nitrogen gas.(e) Sodium oxide and nitrogen gas.

(d) Sodium and nitrogen gas.

Slide68 l.jpg


  • # What are the products of the given decomposition reaction?

  • By definition, oxidation-reduction reactions occur when electrons are transferred from the atom that is oxidized to the atom that is reduced. We need to look for changes in the oxidation states of the elements in the reaction.

    • In the reactants, the oxidation state(s) of the element Na is/are (1). In the product, the oxidation state(s) is/are (0).Therefore, the reaction causes a change in oxidation state.

    • Therefore, this is an oxidation reduction reaction.

  • By definition, a Binary Ionic-Compound Decomposition Reaction occurs when a binary ionic compound is heated.

  • Therefore, this reaction is a Binary-Ionic Compound Decomposition reaction.

  • In general, a Binary Ionic-Compound Decomposition Reaction converts a binary ionic-compound into basic elements.

  • In this reaction, NaN3 reacts to produce Na and N2. # The products of the decomposition reaction are:     

(d) Sodium and nitrogen gas.

The work of Bruce Porter et al here at UT