Lecture 1: Introduction Heshaam Faili [email protected]. ir University of Tehran What is AI ? Foundations of AI The History of AI State of the Art
Jan 04, 2016
Lecture 1: Introduction
Heshaam [email protected]
University of Tehran
What is AI?
Foundations of AIThe History of AIState of the Art
2
Definitions of AI
Develop programs/systems that perform/act like humans
Develop programs/systems that perform/act rationally
Understand human intelligence Formalize the laws of thought and
action
INTELLIGENT AGENTS
3
HUMAN COMPUTER/
HUMAN- types in questions- receives answers on screen
- processes questions- returns answers
What is AI?
Acting Humanly:The Turing Test
If the human cannot tell if it is a computer or a human, the program exhibits intelligence
4
Turing Test Simple Turing test involve
NLP Knowledge representation Automated reasoning Machine learning
To enhance should have Computer vision robotics
AI researchers have devoted little effort to passing the Turing test,
believing that it is more important to study the underlying principles of in- intelligence than to
duplicate an exemplar. The quest for "artificial flight" succeeded when the
Wright brothers and others stopped imitating birds and learned about
aerodynamics.
5
Thinking humanly Cognitive modeling
Computer model together experimental technique from psychology
We will not attempt to describe what is known of human cognition
We will occasionally comment on similarities or differences between AI techniques and human cognition.
6
Thinking rationally
The "laws of thought" approach Aristotle’s “right thinking”
Pattern for argument structure yield correct conclusion
E.g : "Socrates is a man; all men are mortal; therefore, Socrates is mortal."
Logic
7
Acting rationally An agent is just something that acts computer agents are expected to
have other attributes that distinguish them from mere "programs,
A rational agent is one that acts so as to achieve the best outcome or, when there is uncertainty, the best expected outcome.
8
Examples of task for AI Play games
tic-tac-toe, chess, backgammon, poker Process natural language
control tower conversation, stock market briefs
Industrial applications plant diagnostics, plan for manufacturing
Expert-level performance molecular biology, computer configuration
9
Why is AI different than conventional programming?
Strive for GENERALITY EXTENSIBILITY
Capture rational deduction patterns Tackle problems with no algorithmic
solution Represent and manipulate KNOWLEDGE,
rather than DATA A new set of representation and
programming techniques: HEURISTICS
10
Example: TIC-TAC-TOE
11
Program 1: hard wired
Code a table of all possible board positions and the transitions between them (state diagram)
Given a position, look in the table for the next move and return
Properties: time efficient, requires lots of storage not extensible: requires a table for other
games
12
Program 2: less hard wired
Use procedures designed for the game: try to place two marks in a row if opponent has two marks in a row, place
mark in third space
Pattern matching to recognize board positions
Can encode different playing strategies Better space efficiency, less time
efficiency Still game-dependent
13
Program 3: AI-like
Represent the state of the game: current board position next legal positions
Use an evaluation function: Rate the next move according to how
likely it will lead to a win look-ahead of possible oponent moves
More general because it embodies a general strategy.
14
Foundations of AI
Philosophy: Aristotle: the first one worked on I: way
of thinking mechanistic views: of behavior materialism or dualism: of mind Empiricism: for generate a knowledge Logical Positivism: all knowledge can
be connected to gather logically
•Can formal rules be used to draw valid conclusions? •How does the mental mind arise from a physical
brain? • Where does knowledge come from? • How does knowledge lead to action?
15
Foundations of AI
Mathematics: algorithms, logic, formalization of mathematics, Incompleteness, NP-completeness, decision theory
•What are the formal rules to draw valid conclusions?
• What can be computed? •How do we reason with uncertain
information?
16
Foundations of AI
Psychology: behaviorism, cognitive science.
Linguistics: grammars, syntax and semantics.
Computer Science: computers, software, theory
Others: neuroscience, economics, game theory.
How do humans and animals think and act?
• How does language relate to thought?
• How can we build an efficient computer?
17
A brief history of AI (1) Gestation (43-56):
automata theory, neural networks, checkers, theorem proving.
Shannon, Turing, Von Neumann, Newell and Simon, Minsky, McCarthy, Darmouth Workshop.
Great expectations (52-69): computers can do more than arithmetic! Physical symbol system General Problem Solver (GPS), better checkers LISP (LISt Processing language): AI
programming language
birth of AI: 1956
"computational rationally”
"a physical symbol system has the necessary and sufficient means for
general intelligent action."
18
A brief history of AI (2) Microworlds: ANALOGY, blocks world
Minsky supervised a series of students who chose limited problems that
appeared to require intelligence to solve.
19
A brief history of AI (3) A dose of reality (66-74):
ELIZA: human-like conversation. limitations of neural networks, genetic
algorithms, machine evolution. acting in the real world: robotics.
Knowledge-based systems (69-79): All previous methods are weak methods !! domain focus: experts systems vs. General
Problem Solvers. DENDRAL(in Chemical experiment),
MYCIN(medical), XCON, etc.
20
A brief history of AI (4) Commercial AI: the ‘80s boom (80-
90) DEC’s R1 computer configuration program:
saving 40$ million in year many expert systems tools companies
(mostly defunct): Symbolic, Teknowledge, etc.
Japan’s 5th generation project: PROLOG. limited success in autonomous robotics and
vision systems.
21
A brief history of AI (5) The 90’s: specialization, quiet
progress neural networks, genetic algorithms probabilistic reasoning and uncertainty learning planning and constraint solving agents autonomous robotics: NAV autonomous
driving van, crater exploration, robot soccer IBM’s Deep Blue beats Kasparov!
22
State of the Art Embedded AI: many use AI techniques
without saying it is AI! Credit card approval (American Express) Consumer electronics (fuzzy logic)
Healthy research in many areas: intelligent agents, machine learning, man-machine interfaces, etc.
More integrative view: acting in the real world (robots, self diagnosing machines)
23
?