artificial intelligence · comprehend ideas, to use language, and to learn. ... greatest successes....
TRANSCRIPT
ARTIFICIAL
INTELLIGENCE
AN INTRODUCTION
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 1
Course Logistics
Course Description This course will introduce the basics of Artificial Intelligence(AI), its scope and
application domains and principles.
Course Material Required:
S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach 2nd Edition
Reference:
George F Luger, Artificial Intelligence: Structures and Strategies for Complex Problem-solving 5th Edition
Elaine Rich and Kevin Knight, Artificial Intelligence: 3rd Edition
Prerequisite • Data Structures
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 2
Course Logistics
Instructor
Zahid Iqbal
Room # B211 ([email protected])
BS (CS) Punjab University (Gold Medalist)
MS (CS) FAST University Islamabad
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 3
Course Logistics
• Grading Policy
• Sessional 25%
• Mid Term 25%
• Final 50%
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 4
Course Contents Outline
Introduction to Artificial Intelligence
Knowledge Representation
Propositional Logic
Predicate Calculus
Search Methods
Learning
Languages for AI (Prolog, LISP)
Natural Language Processing
Automated Reasoning
Knowledge Based Systems
. . .
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 5
INTRODUCTION
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 6
Intelligence
• What is Intelligence?
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 7
Intelligence (Attempted Definitions)
• Intelligence is an umbrella term used to describe a property of the
mind that encompasses many related abilities, such as the capacities
to reason, to plan, to solve problems, to think abstractly, to
comprehend ideas, to use language, and to learn.
• The ability to learn, reason, and problem solving. Debate revolves
around the nature of intelligence as to whether it is an innate quality
or something that is developed as a result of interacting with the
environment. Many researchers believe that it is a combination of the
two.
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 8
Intelligence (Attempted Definitions)
• Intelligence refers to the various verbal and nonverbal skills and
aptitudes one uses to cope with, interact with, and manipulate the
outside world.
• Intelligence is effectively perceiving, interpreting and responding to
the environment. It is also taken to mean the ability of an organization
to survive and meet desired goals and objectives.
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 9
Artificial Intelligence
• AI may be defined as the branch of computer science that is
concerned with the automation of intelligent behavior.
• The major problem in defining the AI are :
proper definition of intelligence itself.
Is intelligence a single faculty, or is it a name for a collection of distinct and unrelated
abilities?
Exactly what happens when learning occurs?
What is creativity? What is intuition?
Can intelligence be inferred from observable behavior, or does it require evidence of
a particular internal mechanism?
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 10
Artificial Intelligence
Is it necessary to pattern an intelligent computer program after what is known about
human intelligence, or is a strict “engineering” approach to the problem sufficient?
Is it even possible to achieve intelligence on a computer, or does an intelligent entity
require the richness of sensation that might be found only in a biological existence?
• These are all unanswered questions and all of them have helped to
shape the problems and solution methodologies that constitute the
core of modern AI.
• Artificial intelligence is still a young discipline, and its structure,
concerns and methods are not clearly defined than those of a more
mature science such as physics.
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 11
History of AI
• The field of AI research was founded at a conference on the
campus of Dartmouth College in1956. The attendees became
the leaders of AI research for many decades. They and their
students wrote programs that were, to most people, simply
astonishing: Computers were solving word problems in
algebra, proving logical theorems and speaking English.
• By the middle of the 1960s, research in the U.S. was heavily
funded by the Department of Defense and laboratories had
been established around the world. AI's founders were
profoundly optimistic about the future of the new field: Herbert
Simon predicted that "machines will be capable, within twenty
years, of doing any work a man can do“.
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 12
History of AI
• They had failed to recognize the difficulty of some of the problems they faced. In 1974, in response to the criticism of Sir James and ongoing pressure from the US Congress to fund more productive projects, both the U.S. and British governments cut off all undirected exploratory research in AI. The next few years, when funding for projects was hard to find, would later be called the "AI winter".
• In the early 1980s, AI research was revived by the commercial success of expert systems , a form of AI program that simulated the knowledge and analytical skills of one or more human experts. By 1985 the market for AI had reached over a billion dollars. At the same time, Japan's fifth generation computer project inspired the U.S and British governments to restore funding for academic research in the field. However, beginning with the collapse of the Lisp Machine market in 1987, AI once again fell into disrepute, and a second, longer lasting AI winter began.
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 13
History of AI
• In the 1990s and early 21st century, AI achieved its
greatest successes. Artificial intelligence is used for
logistics, data mining, medical diagnosis and many other
areas throughout the technology industry. The success
was due to several factors:
• the increasing computational power of computers,
• a greater emphasis on solving specific sub problems ,
• the creation of new ties between AI and other fields
working on similar problems
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 14
Strong AI and Weak AI
• Strong AI means that machines act intelligently and they
have real conscious minds.
• Weak AI says that machines can be made to act as if they
are intelligent.
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 15
Success Stories • Deep Blue defeated the reigning world chess champion Garry
Kasparov in 1997
• 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
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 16
Example: DARPA CHALLENGE
• Grand Challenge • Cash prizes ($1 to $2 million) offered to first robots to complete a long
course completely unassisted • Stimulates research in vision, robotics, planning, machine learning,
reasoning, etc.
• 2004 Grand Challenge: • 150 mile route in Nevada desert • Furthest any robot went was about 7 miles • … but hardest terrain was at the beginning of the course
• 2005 Grand Challenge: • 132 mile race • Narrow tunnels, winding mountain passes, etc • Stanford 1st, CMU 2nd, both finished in about 6 hours
• 2007 Urban Grand Challenge • In Victorville, California
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 17
Stanley Robot Stanford Racing Team www.stanfordracing.org
2004: Barstow, CA, to Primm, NV
150 mile off-road robot race across
the Mojave desert
Natural and manmade hazards
No driver, no remote control
Fastest vehicle wins the race (and 2
million dollar prize)
HAL: from the movie 2001
• HAL
– part of the story centers around an intelligent computer called HAL
– HAL is the “brains” of an intelligent spaceship
– in the movie, HAL can
• speak easily with the crew
• see and understand the emotions of the crew
• navigate the ship automatically
• diagnose on-board problems
• make life-and-death decisions
• display emotions
• In 1969 this was science fiction: is it still science fiction?
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 20
Can we build hardware as complex as the
brain?
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 21
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
• 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!
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 22
Can Computers beat Humans at Chess?
• Chess Playing is a classic AI problem • well-defined problem
• very complex: difficult for humans to play well
• Conclusion: • YES: today’s computers can beat even the best human
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 23
1200
1400
1600
1800
2000
2200
2400
2600
2800
3000
1966 1971 1976 1981 1986 1991 1997
Ratings
Po
ints
Ra
tin
gs
Human World Champion
Deep Blue
Deep Thought
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
• Conclusion: • NO, for complete sentences
• YES, for individual words
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 24
Can Computers “see”?
• Recognition v. 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?
• Conclusion: • mostly NO: computers can only “see” certain types of objects under limited
circumstances
• YES for certain constrained problems (e.g., face recognition)
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 25
Intelligent Systems in Everyday Life
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 26
Intelligent Systems in Everyday Life
• 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
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 27
Different Types of Artificial Intelligence
1.Modeling exactly how humans actually think
2.Modeling exactly how humans actually act
3.Modeling how ideal agents “should think”
4.Modeling how ideal agents “should act”
• Modern AI focuses on the last definition
• we will also focus on this “engineering” approach
• success is judged by how well the agent performs
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 28
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
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 29
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
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 30
Summary of Today’s Lecture
• Artificial Intelligence involves the study of: • automated recognition and understanding of signals
• reasoning, planning, and decision-making
• learning and adaptation
• AI has made substantial progress in • recognition and learning
• some planning and reasoning problems
• …but many open research problems
• AI Applications • improvements in hardware and algorithms => AI applications in
industry, finance, medicine, and science.
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 31
References
• Artificial Intelligence: Structures and Strategies for
Complex Problem Solving
• Chapter 1
Artificial Intelligence 2012 Lecture 01 Delivered By Zahid Iqbal 32