2. Overview
Introduction of AI
AI problems
The underlying assumption
An AI technique
The level of the model
One Final Word
Prepared by: Prof. Khushali B Kathiriya
2
4. Introduction of AI
What is AI…?
Human mental activities
Needs of AI…
AI= Artificial + Intelligence
Prepared by: Prof. Khushali B Kathiriya
4
5. What is AI can do write now..?
Game planning
Autonomous control
Autonomous planning and scheduling
Diagnosis
Logistic planning
Robotics
Language understanding and problem solving
Prepared by: Prof. Khushali B Kathiriya
5
6. HISTORY OF AI
1943: early beginnings
McCulloch & Pitts: Boolean circuit model of brain
1950: Turing
McCulloch & Pitts: Boolean circuit model of brain
1956: birth of AI
Dartmouth meeting: "Artificial Intelligence“ name adopted
1950s: initial promise
Early AI programs, including
Samuel's checkers program
Newell & Simon's Logic Theorist
1955-65: “great enthusiasm”
Newell and Simon: GPS, general problem solver’’
Gelertner: Geometry Theorem Prover
McCarthy: invention of LISP
Prepared by: Prof. Khushali B Kathiriya
6
7. HISTORY OF AI (Cont.)
1966—73: Reality dawns
Realization that many AI problems are intractable
Limitations of existing neural network methods identified
Neural network research almost disappears
1969—85: Adding domain knowledge
Development of knowledge-based systems
Success of rule-based expert systems,
E.g., DENDRAL, MYCIN
But were brittle and did not scale well in practice
1986-- Rise of machine learning
Neural networks return to popularity
Major advances in machine learning algorithms and applications
Prepared by: Prof. Khushali B Kathiriya
7
8. HISTORY OF AI (Cont.)
1990-- Role of uncertainty
Bayesian networks as a knowledge representation framework
1995-- AI as Science
Integration of learning, reasoning, knowledge representation
AI methods used in vision, language, data mining, etc
Prepared by: Prof. Khushali B Kathiriya
8
9. CAN WE BUILD HARDWARE AS COMPLEX AS
THE BRAIN.?
How complicated is our brain?
a neuron, or nerve cell, is the basic information processing unit
estimated to be on the order of 10 12 neurons in a human brain
many more synapses (10 14) connecting these neurons
cycle time: 10 -3 seconds (1 millisecond)
How complex can we make computers?
108 or more transistors per CPU
supercomputer: hundreds of CPUs, 1012 bits of RAM
cycle times: order of 10 - 9 seconds
Prepared by: Prof. Khushali B Kathiriya
9
10. CAN WE BUILD HARDWARE AS COMPLEX AS
THE BRAIN.? (Cont.)
Conclusion
YES: in the near future we can have computers with as many basic processing
elements as our brain, but with
far fewer interconnections (wires or synapses) than the brain
much faster updates than the brain
But building hardware is very different from making a computer behave like a
brain!
Prepared by: Prof. Khushali B Kathiriya
10
11. CAN COMPUTERS BEAT HUMANS AT CHESS?
Chess Playing is a classic AI problem
well-defined problem
very complex: difficult for humans to play well
1200
1400
1600
1800
2000
2200
2400
2600
2800
3000
1966 1971 1976 1981 1986 1991 1997
Ratings
Human World Champion Deep Blue
Deep Thought
Points
Ratings
Prepared by: Prof. Khushali B Kathiriya
11
12. CAN COMPUTERS BEAT HUMANS AT CHESS?
(Cont.)
Conclusion
YES: today’s computers can beat even the best human
Exercise (Class work):- find current status of chess playing
Prepared by: Prof. Khushali B Kathiriya
12
13. CAN COMPUTERS TALK?
This is known as “speech synthesis”
translate text to phonetic form
e.g., “fictitious” -> fik-tish-es
use pronunciation rules to map phonemes to actual sound
e.g., “tish” -> sequence of basic audio sounds
Difficulties
sounds made by this “lookup” approach sound unnatural
sounds are not independent
e.g., “act” and “action”
modern systems (e.g., at AT&T) can handle this pretty well
a harder problem is emphasis, emotion, etc
humans understand what they are saying
machines don’t: so they sound unnatural
Prepared by: Prof. Khushali B Kathiriya
13
14. CAN COMPUTERS TALK? (Cont.)
Conclusion:
NO, for complete sentences
YES, for individual words
Prepared by: Prof. Khushali B Kathiriya
14
15. RECOGNIZING HUMAN SPEECH
Recognizing normal speech is much more difficult
Speech is continuous: where are the boundaries between words?
e.g., “John’s car has a flat tire”
Large vocabularies
can be many thousands of possible words
we can use context to help figure out what someone said
e.g., hypothesize and test
try telling a waiter in a restaurant:
“I would like some dream and sugar in my coffee”
Background noise, other speakers, accents, colds, etc.
On normal speech, modern systems are only about 60-70% accurate
Prepared by: Prof. Khushali B Kathiriya
15
16. RECOGNIZING HUMAN SPEECH (Cont.)
Conclusion:
NO, normal speech is too complex to accurately recognize
YES, , for restricted problems (small vocabulary, single speaker)
Prepared by: Prof. Khushali B Kathiriya
16
17. CAN COMPUTERS UNDERSTAND SPEECH?
Understanding is different to recognition:
“Time flies like an arrow”
assume the computer can recognize all the words
how many different interpretations are there?
1. time passes quickly like an arrow?
2. command: only time those flies which are like an arrow
3. “time-flies” are fond of arrows
only 1. makes any sense,
but how could a computer figure this out?
clearly humans use a lot of implicit commonsense knowledge in
communication
Prepared by: Prof. Khushali B Kathiriya
17
18. CAN COMPUTERS UNDERSTAND SPEECH?
(Cont.)
Conclusion:
NO, much of what we say is beyond the capabilities of a computer to
understand at present
Prepared by: Prof. Khushali B Kathiriya
18
19. CAN COMPUTERS LEARN AND ADAPT ?
Learning and Adaptation
consider a computer learning to drive on the freeway
we could teach it lots of rules about what to do
or we could let it drive and steer it back on course when it heads for the
embankment
systems like this are under development (e.g., Daimler Benz)
e.g., RALPH at CMU
in mid 90’s it drove 98% of the way from Pittsburgh to San Diego
without any human assistance
Prepared by: Prof. Khushali B Kathiriya
19
20. CAN COMPUTERS LEARN AND ADAPT ?
(Cont.)
Learning and Adaptation
Machine learning allows computers to learn to do things without explicit
programming
Many successful applications:
requires some “set-up”: does not mean your PC can learn to forecast the
stock market or become a brain surgeon
Conclusion
YES, computers can learn and adapt, when presented with information in the
appropriate way
Prepared by: Prof. Khushali B Kathiriya
20
21. CAN COMPUTERS “SEE”?
Recognition vs. Understanding (like Speech)
Recognition and Understanding of Objects in a scene
look around this room
you can effortlessly recognize objects
human brain can map 2d visual image to 3d “map”
Why is visual recognition a hard problem?
Prepared by: Prof. Khushali B Kathiriya
21
22. CAN COMPUTERS “SEE”? (Cont.)
Conclusion
Mostly NO: computers can only “see” certain types of objects under limited
circumstances
YES for certain constrained problems (e.g., face recognition)
Prepared by: Prof. Khushali B Kathiriya
22
23. CAN COMPUTERS PLAN AND MAKE
OPTIMAL DECISIONS?
Intelligence
Involves solving problems and making decisions and plans
e.g., you want to take a holiday in Brazil
you need to decide on dates, flights
you need to get to the airport, etc.
involves a sequence of decisions, plans, and actions
Prepared by: Prof. Khushali B Kathiriya
23
24. CAN COMPUTERS PLAN AND MAKE
OPTIMAL DECISIONS? (Cont.)
What makes planning hard?
the world is not predictable:
your flight is canceled or there’s a backup on the 405
there are a potentially huge number of details
do you consider all flights? all dates?
no: commonsense constrains your solutions
AI systems are only successful in constrained planning problems
Conclusion
NO, real-world planning and decision-making is still beyond the capabilities of
modern computers
exception: very well-defined, constrained problems
Prepared by: Prof. Khushali B Kathiriya
24
25. WHAT’S INVOLVED IN INTELLIGENCE?
Perceiving, recognizing, understanding the real world
Reasoning and planning about the external world
Learning and adaptation
Prepared by: Prof. Khushali B Kathiriya
25
27. Approaches of AI
Systems that
think like humans
Systems that
think rationally
Systems that act
like humans
Systems that act
rationally
Prepared by: Prof. Khushali B Kathiriya
27
28. I) ACTING RATIONALLY
Agent: something that acts
Rational agent: one that acts so as to achieve best outcome or if there is
uncertainty ,best possible outcome.
Emphasis is on autonomous agents that behave rationally (make the best
predictions, take the best actions)
on average over time
within computational limitations (“bounded rationality”)
Advantages of this view:-
1. More general then “thinking rational”
2. More appropriate for scientific development.
Prepared by: Prof. Khushali B Kathiriya
28
29. II) THINKING RATIONALLY
Represent facts about the world via logic
Logic concept (law of thought) given by Aristotle
Use logical inference as a basis for reasoning about these facts
Ex :- Hiren is man. Man is mortal. So Hiren is mortal.
Can be a very useful approach to AI
E.g., theorem-provers
Limitations
Has no way to represent goals, costs, etc. (important aspects of real-world environments)
For uncertain knowledge cant have logical representation
Can need large computational resources to solve problems
Prepared by: Prof. Khushali B Kathiriya
29
30. III) ACTING HUMANLY: TURING TEST
Turing (1950) "Computing machinery and intelligence”
"Can machines think?"
"Can machines behave intelligently?“
Operational test for intelligent behavior: the Imitation Game
Suggests major components required for AI:
- knowledge representation
- reasoning,
- language/image understanding,
- learning
Question: Is it important that an intelligent system act like a human?
Prepared by: Prof. Khushali B Kathiriya
30
31. IV) THINKING HUMANLY
Cognitive Science approach
Try to get “inside” our minds
E.g., conduct experiments with people to try to “reverse-engineer” how we
reason, learning, remember, predict
Problems
Humans don’t behave rationally
The reverse engineering is very hard to do
The brain’s hardware is very different to a computer program
Prepared by: Prof. Khushali B Kathiriya
31
32. “CHINESE ROOM” ARGUMENT [SEARLE 1980]
Person who knows English but not Chinese sits in room
Receives notes in Chinese
Has systematic English rule book for how to write new Chinese characters based on
input Chinese characters, returns his notes
Person=CPU, rule book=AI program, really also need lots of paper (storage)
Has no understanding of what they mean
But from the outside, the room gives perfectly reasonable answers in Chinese!
Searle’s argument: the room has no intelligence in it!
Prepared by: Prof. Khushali B Kathiriya
32
34. Task Domains of AI
1. Mundane Task
Perception
Vision
Speech
Natural Languages
Understanding
Generation
Translation
Common sense reasoning
Robot control
Prepared by: Prof. Khushali B Kathiriya
34
35. Task Domains of AI
2. Formal Task
Games: chess, checkers etc.
Math: geometric, logic, proving properties of programs
3. Expert Task
Engineering (Design, fault finding, manufacturing planning)
Scientific analysis
Medical analysis
Financial analysis
Prepared by: Prof. Khushali B Kathiriya
35
36. AI Problems
3*3*3 Rubik’s cube problem
Prepared by: Prof. Khushali B Kathiriya
36
42. What is an AI Technique?
AI has a very variety of problems and all of them require different approaches or
techniques to solve them.
It come with some limitations
It is voluminous
It is hard to characterize accurately
It is constantly changing
The format is quiet different to put it directly to use
Prepared by: Prof. Khushali B Kathiriya
42
43. What is an AI Technique? (Cont.)
1. Describe and match
2. Goal reduction
3. Tree searching
4. Constraint satisfaction
5. Generate and test
6. Rule based system
Prepared by: Prof. Khushali B Kathiriya
43
44. What is an AI Technique? (Cont.)
Computational model
Prepared by: Prof. Khushali B Kathiriya
44
1. Describe and match
Initial state
Goal state
45. What is an AI Technique? (Cont.)
2. Tree Searching
AI is broadly classified as uniformed searching and informed searching.
Prepared by: Prof. Khushali B Kathiriya
45
Un-informed Search Informed Search
DFS (Depth First Search) Hill Climbing
BFS (Breadth First Search) BFS (Best First Search)
UCS (Uniform Cost Search) A* Search
DLS(Depth Limited Search) Iterative Depending A*
Iterative Depending DFS Beam Search
Bidirectional Search AO* Search
46. What is an AI Technique? (Cont.)
3. Goal Reduction
4. Generate and Test
Prepared by: Prof. Khushali B Kathiriya
46
47. What is an AI Technique? (Cont.)
5. Rule based system
It’s a simplest form they have set of rules and interpreter and input from the
environment. Rules are of the form IF<condition> THEN<action>.
Prepared by: Prof. Khushali B Kathiriya
47
49. SUCCESS STORIES
Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997
AI program proved a mathematical conjecture (Robbins conjecture) unsolved for
decades
During the 1991 Gulf War, US forces deployed an AI logistics planning and
scheduling program that involved up to 50,000 vehicles, cargo, and people
NASA's on-board autonomous planning program controlled the scheduling of
operations for a spacecraft
Proverb solves crossword puzzles better than most humans
Robot driving: DARPA grand challenge 2003-2007
2006: face recognition software available in consumer cameras
Prepared by: Prof. Khushali B Kathiriya
49
Father of AI:
John McCarthy
50. INTELLIGENT SYSTEMS IN YOUR EVERYDAY LIFE
Post Office
automatic address recognition and sorting of mail
Banks
automatic check readers, signature verification systems
automated loan application classification
Customer Service
automatic voice recognition
The Web
Identifying your age, gender, location, from your Web surfing
Automated fraud detection
Digital Cameras
Automated face detection and focusing
Computer Games
Intelligent characters/agents
Prepared by: Prof. Khushali B Kathiriya
50
51. SUB-FIELDS OF ARTIFICIAL INTELLIGENCE
Neural Networks – e.g. brain modelling, time series prediction, classification
Evolutionary Computation – e.g. genetic algorithms, genetic programming
Vision – e.g. object recognition, image understanding
Robotics – e.g. intelligent control, autonomous exploration
Expert Systems – e.g. decision support systems, teaching systems
Speech Processing– e.g. speech recognition and production
Natural Language Processing – e.g. machine translation
Planning – e.g. scheduling, game playing
Machine Learning – e.g. decision tree learning, version space learning
Prepared by: Prof. Khushali B Kathiriya
51
52. One final word
Ai is a filed in which we have lot is different types of hard problems to be solved.
The catch is whether they are solved by mimicking the human intelligence or just
by any techniques that is easy to use.
In simple words, AI system world like human brain, where a machine or software
shows intelligence while performing given tasks; such systems are called
Intelligent systems or Expert system.
AI is study of how to make machine do thing which at the moment people do
better.
Prepared by: Prof. Khushali B Kathiriya
52