Artificial intelligence

Umesh Meher
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?
"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
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
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.
academic $ academic and routine
The Origins of AI Hype
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
•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
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
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
40 50 60 70 80 90 00 10
The Origins of Symbolic AI
• Games
•Theorem proving
Games
• 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
Games
• AI in Role Playing Games – now we need knowledge
Logic Theorist
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 Theorist
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 Theorist
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 Theorist
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
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
AM “discovered”:
• Goldbach’s conjecture
• Unique prime factorization theorem
What About Things that People Do
Easily?
• Common sense reasoning
• Vision
• Moving around
• Language
What About Things People Do
Easily?
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
•Why do we need it?
•How can we represent it and use it?
•How can we acquire it?
Find me stuff about dogs who save people’s lives.
Why?
•Why do we need it?
•How can we represent it and use it?
•How can we acquire it?
Find me stuff about dogs who save people’s lives.
Two beagles spot a fire.
Their barking alerts
neighbors, who call 911.
Even Children Know a Lot
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
What’s a party?
What’s a kite?
What’s a piggy bank?
What is a Concept?
Let’s start with an easy one: chair
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
Chair?
How Can We Teach Things to Computers?
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
If dogs are mammals and mammals are animals, are dogs
mammals?
Some Things Are Harder
If most Canadians have brown eyes, and most brown eyed people
have good eyesight, then do most Canadians have good eyesight?
Some Things Are Harder
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
Pat Winston’s program (1970) learned concepts in the
blocks micro-world.
Concept Acquisition
The arch concept:
Further Complications from How
Language is Used
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
I need a new bonnet.
The senator moved to table the bill.
Compiling Common Sense
Knowledge
• CYC (http://www.cyc.com)
• UT (http://www.cs.utexas.edu/users/mfkb/RKF/tree/ )
• WordNet (http://www.cogsci.princeton.edu/~wn/)
Distributed Knowledge Acquisition
• Acquiring knowledge for use by people
• Oxford English Dictionary
(http://oed.com/about/contributors/ )
• Wikipedia
• Acquiring knowledge for use by programs
• ESP (http://www.espgame.org/)
• Open Mind (http://commons.media.mit.edu:3000/)
• CYC (http://www.cyc.com)
Reasoning
We can describe reasoning as search in a space of
possible situations.
Breadth-First Search
Depth-First Search
The British Museum Algorithm
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
http://www.arn.org/docs2/news/monkeysandtypewriters051103.htm
A Version of Depth-First Search:
Branch 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
(800)
Stay E $250
(850)
Total cost
(1200)
Problem Reduction
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
Problem: You have just arrived in Washington, D.C.
You’re in your car, trying to get downtown to the
Washington Monument.
Hill Climbing – Some Problems
Hill Climbing – Is Close Good
Enough?
A
B
Is A good enough?
• Choose winning lottery numbers
Hill Climbing – Is Close Good
Enough?
A
B
Is A good enough?
• Choose winning lottery numbers
• Get the cheapest travel itinerary
• Clean the house
Expert Systems
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
Mass spectometry
Ketone group:
Expert Systems
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
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
eXpertise2Go: http://www.expertise2go.com/
AcquiredIntelligence: http://www.aiinc.ca/demos/
(whales, graduate school)
Taking the AP Chemistry Exam
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.
SYSTEM-GENERATED ANSWER:
# 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
Artificial intelligence
1 of 68

Recommended

Artificial intelligence- The science of intelligent programs by
Artificial intelligence- The science of intelligent programsArtificial intelligence- The science of intelligent programs
Artificial intelligence- The science of intelligent programsDerak Davis
2K views19 slides
Artificial intelligence by
Artificial intelligenceArtificial intelligence
Artificial intelligencesaloni sharma
4.4K views46 slides
ARTIFICIAL INTELLIGENCE by
ARTIFICIAL INTELLIGENCEARTIFICIAL INTELLIGENCE
ARTIFICIAL INTELLIGENCEMidhuti
4.7K views21 slides
Artificial intelligence by
Artificial intelligenceArtificial intelligence
Artificial intelligenceIndranil Chowdhury
2.5K views34 slides
Artificial intelligence by
Artificial intelligenceArtificial intelligence
Artificial intelligenceSai Nath
5.2K views30 slides
artificial intelligence by
artificial intelligenceartificial intelligence
artificial intelligencevallibhargavi
159K views27 slides

More Related Content

What's hot

Artificial intelligence by
Artificial intelligenceArtificial intelligence
Artificial intelligencegayathrysatheesan1
6.3K views25 slides
Artificial intelligence by
Artificial intelligenceArtificial intelligence
Artificial intelligenceGuduru Lakshmi Kiranmai
12.5K views25 slides
History of AI, Current Trends, Prospective Trajectories by
History of AI, Current Trends, Prospective TrajectoriesHistory of AI, Current Trends, Prospective Trajectories
History of AI, Current Trends, Prospective TrajectoriesGiovanni Sileno
692 views166 slides
best presentation Artitficial Intelligence by
best presentation Artitficial Intelligencebest presentation Artitficial Intelligence
best presentation Artitficial Intelligencejennifer joe
741 views33 slides
Understanding Artificial intelligence by
Understanding Artificial intelligenceUnderstanding Artificial intelligence
Understanding Artificial intelligenceIla Group
2.9K views13 slides
Introduction to Artificial Intelligence and few examples by
Introduction to Artificial Intelligence and few examplesIntroduction to Artificial Intelligence and few examples
Introduction to Artificial Intelligence and few examplesBMS Institute of Technology
17.9K views31 slides

What's hot(20)

History of AI, Current Trends, Prospective Trajectories by Giovanni Sileno
History of AI, Current Trends, Prospective TrajectoriesHistory of AI, Current Trends, Prospective Trajectories
History of AI, Current Trends, Prospective Trajectories
Giovanni Sileno692 views
best presentation Artitficial Intelligence by jennifer joe
best presentation Artitficial Intelligencebest presentation Artitficial Intelligence
best presentation Artitficial Intelligence
jennifer joe741 views
Understanding Artificial intelligence by Ila Group
Understanding Artificial intelligenceUnderstanding Artificial intelligence
Understanding Artificial intelligence
Ila Group2.9K views
Artificial Intelligence PPT . by VAIBHAVNAGPURE6
Artificial Intelligence PPT .Artificial Intelligence PPT .
Artificial Intelligence PPT .
VAIBHAVNAGPURE66.1K views
artificial intelligence and its applications by Yogendra Vishnoi
 artificial intelligence and its applications artificial intelligence and its applications
artificial intelligence and its applications
Yogendra Vishnoi59.1K views
PPT on Artificial Intelligence(A.I.) by Aakanksh Nath
PPT on Artificial Intelligence(A.I.) PPT on Artificial Intelligence(A.I.)
PPT on Artificial Intelligence(A.I.)
Aakanksh Nath4.7K views
Artificial Intelligence PowerPoint Presentation Slide Template Complete Deck by SlideTeam
Artificial Intelligence PowerPoint Presentation Slide Template Complete DeckArtificial Intelligence PowerPoint Presentation Slide Template Complete Deck
Artificial Intelligence PowerPoint Presentation Slide Template Complete Deck
SlideTeam1.1K views
Artificial Intelligence by Dhrumil Shah
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
Dhrumil Shah5.6K views
Artifical intelligence-NIT Kurukshetra by Narendra Panwar
Artifical intelligence-NIT KurukshetraArtifical intelligence-NIT Kurukshetra
Artifical intelligence-NIT Kurukshetra
Narendra Panwar3.9K views
Artificial Intelligence by u053675
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
u053675241.9K views
Technologies Demystified: Artificial Intelligence by Pioneers.io
Technologies Demystified: Artificial IntelligenceTechnologies Demystified: Artificial Intelligence
Technologies Demystified: Artificial Intelligence
Pioneers.io 2.5K views
Artificial intelligence tapan by Tapan Khilar
Artificial intelligence tapanArtificial intelligence tapan
Artificial intelligence tapan
Tapan Khilar2.1K views
ARTIFICIAL INTELLIGENCE Presentation by Muhammad Ahmed
ARTIFICIAL INTELLIGENCE PresentationARTIFICIAL INTELLIGENCE Presentation
ARTIFICIAL INTELLIGENCE Presentation
Muhammad Ahmed7K views
Artificial intelligence by funpathshala
Artificial intelligenceArtificial intelligence
Artificial intelligence
funpathshala2.1K views
artificial intelligence by vallibhargavi
artificial intelligenceartificial intelligence
artificial intelligence
vallibhargavi3.4K views

Similar to Artificial intelligence

Intoduction of Artificial Intelligence by
Intoduction of Artificial IntelligenceIntoduction of Artificial Intelligence
Intoduction of Artificial IntelligenceBabasaheb Bhimrao Ambedakar University
766 views68 slides
Artificial Intelligence by
Artificial IntelligenceArtificial Intelligence
Artificial Intelligenceअशोक पचौरी
629 views68 slides
Artificial intelligence.pptx by
Artificial intelligence.pptxArtificial intelligence.pptx
Artificial intelligence.pptxMuahmmad Rafiq
25 views30 slides
Artificial Intelligence by
Artificial IntelligenceArtificial Intelligence
Artificial IntelligenceIman Ardekani
2.5K views34 slides
The IOT Academy Training for Artificial Intelligence ( AI) by
The IOT Academy Training for Artificial Intelligence ( AI)The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy Training for Artificial Intelligence ( AI)The IOT Academy
115 views33 slides
Lecture 1 by
Lecture 1Lecture 1
Lecture 1Nepal Telecom
1.4K views68 slides

Similar to Artificial intelligence(20)

Artificial Intelligence by Iman Ardekani
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
Iman Ardekani2.5K views
The IOT Academy Training for Artificial Intelligence ( AI) by The IOT Academy
The IOT Academy Training for Artificial Intelligence ( AI)The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy Training for Artificial Intelligence ( AI)
The IOT Academy115 views
Artificial intelligence by mailmerk
Artificial intelligenceArtificial intelligence
Artificial intelligence
mailmerk3.7K views
Artificial Intelligence - Past, Present and Future by Grigory Sapunov
Artificial Intelligence - Past, Present and FutureArtificial Intelligence - Past, Present and Future
Artificial Intelligence - Past, Present and Future
Grigory Sapunov47.9K views
Normal Considered Harmful by greenwop
Normal Considered HarmfulNormal Considered Harmful
Normal Considered Harmful
greenwop1.9K views
Machine Learning, AI and the Brain by TechExeter
Machine Learning, AI and the Brain Machine Learning, AI and the Brain
Machine Learning, AI and the Brain
TechExeter800 views
Artificial Intelligence by Akshay Thakur
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
Akshay Thakur1.4K views
Artificial Intelligence by Bise Mond
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
Bise Mond7K views

Recently uploaded

START Newsletter 3 by
START Newsletter 3START Newsletter 3
START Newsletter 3Start Project
7 views25 slides
Design_Discover_Develop_Campaign.pptx by
Design_Discover_Develop_Campaign.pptxDesign_Discover_Develop_Campaign.pptx
Design_Discover_Develop_Campaign.pptxShivanshSeth6
49 views20 slides
Design of machine elements-UNIT 3.pptx by
Design of machine elements-UNIT 3.pptxDesign of machine elements-UNIT 3.pptx
Design of machine elements-UNIT 3.pptxgopinathcreddy
37 views31 slides
GDSC Mikroskil Members Onboarding 2023.pdf by
GDSC Mikroskil Members Onboarding 2023.pdfGDSC Mikroskil Members Onboarding 2023.pdf
GDSC Mikroskil Members Onboarding 2023.pdfgdscmikroskil
63 views62 slides
Renewal Projects in Seismic Construction by
Renewal Projects in Seismic ConstructionRenewal Projects in Seismic Construction
Renewal Projects in Seismic ConstructionEngineering & Seismic Construction
5 views8 slides
Créativité dans le design mécanique à l’aide de l’optimisation topologique by
Créativité dans le design mécanique à l’aide de l’optimisation topologiqueCréativité dans le design mécanique à l’aide de l’optimisation topologique
Créativité dans le design mécanique à l’aide de l’optimisation topologiqueLIEGE CREATIVE
8 views84 slides

Recently uploaded(20)

Design_Discover_Develop_Campaign.pptx by ShivanshSeth6
Design_Discover_Develop_Campaign.pptxDesign_Discover_Develop_Campaign.pptx
Design_Discover_Develop_Campaign.pptx
ShivanshSeth649 views
Design of machine elements-UNIT 3.pptx by gopinathcreddy
Design of machine elements-UNIT 3.pptxDesign of machine elements-UNIT 3.pptx
Design of machine elements-UNIT 3.pptx
gopinathcreddy37 views
GDSC Mikroskil Members Onboarding 2023.pdf by gdscmikroskil
GDSC Mikroskil Members Onboarding 2023.pdfGDSC Mikroskil Members Onboarding 2023.pdf
GDSC Mikroskil Members Onboarding 2023.pdf
gdscmikroskil63 views
Créativité dans le design mécanique à l’aide de l’optimisation topologique by LIEGE CREATIVE
Créativité dans le design mécanique à l’aide de l’optimisation topologiqueCréativité dans le design mécanique à l’aide de l’optimisation topologique
Créativité dans le design mécanique à l’aide de l’optimisation topologique
LIEGE CREATIVE8 views
Ansari: Practical experiences with an LLM-based Islamic Assistant by M Waleed Kadous
Ansari: Practical experiences with an LLM-based Islamic AssistantAnsari: Practical experiences with an LLM-based Islamic Assistant
Ansari: Practical experiences with an LLM-based Islamic Assistant
M Waleed Kadous9 views
_MAKRIADI-FOTEINI_diploma thesis.pptx by fotinimakriadi
_MAKRIADI-FOTEINI_diploma thesis.pptx_MAKRIADI-FOTEINI_diploma thesis.pptx
_MAKRIADI-FOTEINI_diploma thesis.pptx
fotinimakriadi12 views
Searching in Data Structure by raghavbirla63
Searching in Data StructureSearching in Data Structure
Searching in Data Structure
raghavbirla6317 views
SUMIT SQL PROJECT SUPERSTORE 1.pptx by Sumit Jadhav
SUMIT SQL PROJECT SUPERSTORE 1.pptxSUMIT SQL PROJECT SUPERSTORE 1.pptx
SUMIT SQL PROJECT SUPERSTORE 1.pptx
Sumit Jadhav 22 views
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf by AlhamduKure
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdfASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf
ASSIGNMENTS ON FUZZY LOGIC IN TRAFFIC FLOW.pdf
AlhamduKure8 views
MongoDB.pdf by ArthyR3
MongoDB.pdfMongoDB.pdf
MongoDB.pdf
ArthyR349 views
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx by lwang78
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx
2023Dec ASU Wang NETR Group Research Focus and Facility Overview.pptx
lwang78180 views
REACTJS.pdf by ArthyR3
REACTJS.pdfREACTJS.pdf
REACTJS.pdf
ArthyR337 views

Artificial intelligence

  • 2. 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.
  • 3. 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
  • 4. 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."
  • 5. Time Line – The Big Picture 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. academic $ academic and routine
  • 6. The Origins of AI Hype 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."
  • 7. Evolution of the Main Ideas •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
  • 8. Symbolic vs. Subsymbolic AI 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))
  • 9. The Origins of Subsymbolic AI 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”
  • 10. Interest in Subsymbolic AI 40 50 60 70 80 90 00 10
  • 11. The Origins of Symbolic AI • Games •Theorem proving
  • 12. Games • 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
  • 13. Games • AI in Role Playing Games – now we need knowledge
  • 14. Logic Theorist 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.
  • 15. Logic Theorist 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
  • 16. Logic Theorist 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.
  • 17. Logic Theorist 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.
  • 18. Mathematics 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.
  • 19. Discovery AM “discovered”: • Goldbach’s conjecture • Unique prime factorization theorem
  • 20. What About Things that People Do Easily? • Common sense reasoning • Vision • Moving around • Language
  • 21. What About Things People Do Easily? 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.
  • 22. They Require Knowledge •Why do we need it? •How can we represent it and use it? •How can we acquire it? Find me stuff about dogs who save people’s lives.
  • 23. Why? •Why do we need it? •How can we represent it and use it? •How can we acquire it? Find me stuff about dogs who save people’s lives. Two beagles spot a fire. Their barking alerts neighbors, who call 911.
  • 24. Even Children Know a Lot 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.
  • 25. We Divide Things into Concepts What’s a party? What’s a kite? What’s a piggy bank?
  • 26. What is a Concept? Let’s start with an easy one: chair
  • 41. How Can We Teach Things to Computers? 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?
  • 42. Some Things are Easy If dogs are mammals and mammals are animals, are dogs mammals?
  • 43. Some Things Are Harder If most Canadians have brown eyes, and most brown eyed people have good eyesight, then do most Canadians have good eyesight?
  • 44. Some Things Are Harder 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.
  • 45. Concept Acquisition Pat Winston’s program (1970) learned concepts in the blocks micro-world.
  • 47. Further Complications from How Language is Used After the strike, the president sent them away. After the strike, the umpire sent them away. The word “strike” refers to two different concepts.
  • 48. When Other Words in Context Aren’t Enough I need a new bonnet. The senator moved to table the bill.
  • 49. Compiling Common Sense Knowledge • CYC (http://www.cyc.com) • UT (http://www.cs.utexas.edu/users/mfkb/RKF/tree/ ) • WordNet (http://www.cogsci.princeton.edu/~wn/)
  • 50. Distributed Knowledge Acquisition • Acquiring knowledge for use by people • Oxford English Dictionary (http://oed.com/about/contributors/ ) • Wikipedia • Acquiring knowledge for use by programs • ESP (http://www.espgame.org/) • Open Mind (http://commons.media.mit.edu:3000/) • CYC (http://www.cyc.com)
  • 51. Reasoning We can describe reasoning as search in a space of possible situations.
  • 54. The British Museum Algorithm 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 http://www.arn.org/docs2/news/monkeysandtypewriters051103.htm
  • 55. A Version of Depth-First Search: Branch 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 (800) Stay E $250 (850) Total cost (1200)
  • 56. Problem Reduction 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.
  • 57. Hill Climbing Problem: You have just arrived in Washington, D.C. You’re in your car, trying to get downtown to the Washington Monument.
  • 58. Hill Climbing – Some Problems
  • 59. Hill Climbing – Is Close Good Enough? A B Is A good enough? • Choose winning lottery numbers
  • 60. Hill Climbing – Is Close Good Enough? A B Is A good enough? • Choose winning lottery numbers • Get the cheapest travel itinerary • Clean the house
  • 61. Expert Systems 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.
  • 62. To Interpret the Rule Mass spectometry Ketone group:
  • 63. Expert Systems 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.
  • 64. Expert Systems – Today: Medicine 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
  • 65. Expert Systems – Today: Build Your Own eXpertise2Go: http://www.expertise2go.com/ AcquiredIntelligence: http://www.aiinc.ca/demos/ (whales, graduate school)
  • 66. Taking the AP Chemistry Exam 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.
  • 67. SYSTEM-GENERATED ANSWER: # 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

Editor's Notes

  1. Herbert A. Simon and Allen Newell, "Heuristic Problem Solving: The Next Advance in Operations Research," Operations Research, January-February 1958, 1-10.
  2. Neural net picture from http://hem.hj.se/~de96klda/NeuralNetworks.htm#2.1.2%20The%20Artificial%20Neuron
  3. http://diwww.epfl.ch/mantra/tutorial/english/mcpits/html/
  4. Note: They’re formal. Don’t need a lot of messy knowledge.
  5. Try friend in Wordnet
  6. From Push Singh Open Mind paper
  7. Two beagles spot fire. Their barking alerts neighbors who call the police.
  8. http://www.pitt.edu/~bookctr/giftsapparel/gradgifts/Chair.jpg
  9. http://www.ecodesignz.com/Merchant2/graphics/00000001/ED_02SideChair_F.jpg No arms.
  10. http://www.branchhome.com/images/large/emil_knit_chair_LRG.jpg
  11. http://www.designspotter.com/weblog/archives/The%20simplest%20chair.jpg
  12. http://www.sarahpeterssculpture.com/web_photos/chair_for_web.jpg
  13. http://images.google.com/imgres?imgurl=http://www.justcoolchairs.com/images/think_chair.jpg&imgrefurl=http://www.justcoolchairs.com/cool_chair.html&h=322&w=300&sz=17&hl=en&start=15&tbnid=tfx_vZ0e8RGnTM:&tbnh=118&tbnw=110&prev=/images%3Fq%3Dchair%26gbv%3D2%26svnum%3D10%26hl%3Den%26sa%3DG
  14. http://images.google.com/imgres?imgurl=http://www.justcoolchairs.com/images/think_chair.jpg&imgrefurl=http://www.justcoolchairs.com/cool_chair.html&h=322&w=300&sz=17&hl=en&start=15&tbnid=tfx_vZ0e8RGnTM:&tbnh=118&tbnw=110&prev=/images%3Fq%3Dchair%26gbv%3D2%26svnum%3D10%26hl%3Den%26sa%3DG
  15. http://images.google.com/imgres?imgurl=http://zedomax.com/blog/wp-content/uploads/2007/05/solar-system-chair.jpg&imgrefurl=http://zedomax.com/blog/tag/space/&h=300&w=300&sz=15&hl=en&start=105&tbnid=F9ZS2RMTee4s8M:&tbnh=116&tbnw=116&prev=/images%3Fq%3Dchair%26start%3D90%26gbv%3D2%26ndsp%3D18%26svnum%3D10%26hl%3Den%26sa%3DN
  16. http://homedecorators.com/images/items/large/l32369.jpg
  17. http://images.google.com/imgres?imgurl=http://germes-online.com/direct/dbimage/50187176/Bar_Stool.jpg&imgrefurl=http://germes-online.com/catalog/26/28/882/21425/bar_stool.html&h=360&w=360&sz=16&hl=en&start=28&tbnid=W0J1VAXlQfRpBM:&tbnh=121&tbnw=121&prev=/images%3Fq%3Dstool%26start%3D18%26gbv%3D2%26ndsp%3D18%26svnum%3D10%26hl%3Den%26sa%3DN
  18. http://images.google.com/imgres?imgurl=http://www.sofaclassics.co.uk/shop/images/CornerSofa_Chester_JO1417.jpg&imgrefurl=http://www.sofaclassics.co.uk/shop/index.php%3FcPath%3D13&h=500&w=500&sz=37&hl=en&start=69&tbnid=mAmvuqkb7fdwXM:&tbnh=130&tbnw=130&prev=/images%3Fq%3Dsofa%26start%3D54%26gbv%3D2%26ndsp%3D18%26svnum%3D10%26hl%3Den%26sa%3DN
  19. auto.howstuffworks.com/child-car-seat2.htm http://auto.howstuffworks.com/child-car-seat2.htm
  20. Quoted by Push Singh in Open Mind paper
  21. Form Push Singh Open Mind paper
  22. Form Push Singh Open Mind paper
  23. From Crevier, AI: The Tumultuous History of the Search for Artificial Intelligence, p. 92.
  24. From Crevier, AI: The Tumultuous History of the Search for Artificial Intelligence, p. 92.
  25. British vs. American meaning of table, but both occur in the parliamentary context.
  26. Try friend in Wordnet
  27. Try friend in Wordnet
  28. Suppose the solution is at depth 4 at the right. Then we must explore almost all paths of length 5 before we find it. Suppose all paths of length 10 are solutions? Note how much memory this approach takes.
  29. Notice how much less memory this takes. Note that we could have generated the answer but not noticed it. Is depth-first search optimal? (I.e., if it finds the solution, it’s the best one) no. Can miss a better one somewhere else in the tree. What’s the worst problem? Can go on forever. Can implement a cut off.
  30. British Museum- find something there by walking randomly. Monkeys and typewriters: enough monkeys, given enough time at enough typewriters, would eventually generate the complete works of Shakespeare.
  31. It’s no longer the case that when we find one goal node we can stop. We want to find the cheapest acceptable trip. So we find one for $1200. We keep looking. But consider what happens when we generate the Fly to C node. Since all costs are positive, we know this trip will be more expensive than the first one we found. We can prune that entire subtree.
  32. Various ways of getting stuck.
  33. Not for these. But see next page.