Lec01: Introduction

Dr. Humera Bashir 1

– Programming
– Data structure
– Pprobability

Will review the

above during the
first couple of
weeks
 Artificial Intelligence: A Modern Approach
by S. Russell and P. Norvig
 Read the textbook!
 Key for learning and obtaining a good grade
 Lecture slides + book = lecture notes!

REFERENCE Book:
 Artificial Intelligence: Foundations of Computational
Agents,
D. Poole and A. Mackworth on

Please interrupt with questions !at any time

To -

 Provide students with in-depth knowledge of important

concepts, problems solving, and techniques in AI

 Introduce students to the basic toolkit of AI algorithms

and representation methods that can be applied to a

wide variety of real world problems.

 AI makes computers more useful
 Intelligent computer would have huge impact
on civilization
 AI cited as “field I would most like to be in” by
scientists in all fields
 Computer is a good metaphor for talking and
thinking about intelligence
 Turning theory into working programs forces
us to work out the details
 Deep Blue defeated the reigning world chess champion Garry
Kasparov in 1997

 Proved a mathematical conjecture (Robbins conjecture)

unsolved for decades

 No hands across America (driving autonomously 98% of the

time from Pittsburgh to San Diego)

 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

 Stanford vehicle in Darpa challenge completed autonomously

a 132 mile desert track in 6 hours 32 minutes.

http://www.youtube.com/watch?v=-xibwwNVLgg
 Philosophy
◦ 450 BC, Socrates asked for algorithm to distinguish pious
from non-pious individuals
◦ Aristotle developed laws for reasoning
 Mathematics
◦ 1847, Boole introduced formal language for making logical
inference
 Economics
◦ 1776, Smith views economies as consisting of agents
maximizing their own well being (payoff)
 Neuroscience
◦ 1861, Study how brains process information
 Psychology
◦ 1879, Cognitive psychology initiated
 Linguistics
◦ 1957, Skinner studied behaviorist approach to language
learning
 CS-based AI started with “Dartmouth Conference” in
1956
 Attendees
◦ John McCarthy
 LISP, application of logic to reasoning
◦ Marvin Minsky
 Popularized neural networks
 Slots and frames
 The Society of the Mind
◦ Claude Shannon
 Computer checkers
 Information theory
 Open-loop 5-ball juggling
◦ Allen Newell and Herb Simon
 General Problem Solver
 Can we make something that is as intelligent as a
human?
 Can we make something that is as intelligent as a bee?
 Can we make something that is evolutionary, self
improving, autonomous, and flexible?
 Can we save this plant $20M/year by pattern
recognition?
 Can we save this bank $50M/year by automatic fraud
detection?
 Can we start a new industry of handwriting recognition
agents?
AI IN SCIENCE FICTION AND
PHILOSOPHY
We will focus on "acting rationally“
Luger & Stubblefield, 1993
“The branch of computer science that is concerned with the automation of intelligent behavior”

Nilsson, 1998
“Many human mental activities such as writing computer programs, doing mathematics, engaging
in common sense reasoning, understanding language, and even driving an automobile, are said
to demand intelligence. We might say that [these systems] exhibit artificial intelligence”

Rich & Knight, 1991

“The study of how to make computers do things at which, at the moment, people are better”

Schalkoff, 1990
“A field of study that seeks to explain and emulate intelligent behavior in terms of computational
processes”

Winston, 1992
“The study of the computations that make it possible to perceive, reason, and act”
 “[The automation of] activities that we
associate with human thinking, activities
such as decision making, problem solving,
learning”
 Turing test: ultimate test for acting humanly
◦ Computer and human both interrogated by judge
◦ Computer passes test if judge can’t tell the difference
 Requires knowledge of brain function
 What level of abstraction?
 How can we validate this
 This is the focus of Cognitive Science
 Aristotle attempted this
 What are correct arguments or thought
processes?
 Provided foundation of much of AI
 Not all intelligent behavior controlled by logic
 What is our goal? What is the purpose of
thinking?
 Act to achieve goals, given set of beliefs
 Rational behavior is doing the “right thing”
◦ Thing which expects to maximize goal achievement
 This is approach adopted by Russell & Norvig
An agent perceives its environment
through sensors and acts on the
environment through actuators.

Human: sensors are eyes, ears,

actuators (effectors) are hands,
legs, mouth.

Robot: sensors are cameras, sonar,

lasers, ladar, bump, effectors are
grippers, manipulators, motors

The agent’s behavior is described by it

function that maps percept to action.
 A rational agent does the right thing
(what is this?)
 A fixed performance measure evaluates the
sequence of observed action effects on the
environment
 Use PEAS to describe task
◦ Performance measure
◦ Environment
◦ Actuators
◦ Sensors
 Use PEAS to describe task environment
◦ Performance measure
◦ Environment
◦ Actuators
◦ Sensors
 Example: Taxi driver
◦ Performance measure: safe, fast, comfortable
(maximize profits)
◦ Environment: roads, other traffic, pedestrians,
customers
◦ Actuators: steering, accelerator, brake, signal, horn
◦ Sensors: cameras, sonar, speedometer, GPS,
odometer, accelerometer, engine sensors
 Fully observable vs. partially observable
 Deterministic vs. stochastic / strategic
 Episodic vs. sequential
 Static vs. dynamic
 Discrete vs. continuous
 Single agent vs. multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock

Chess without a
clock

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obser Determi Episodic Static Discrete Agents
vable nistic
Chess with a clock Fully Strategic Sequential Semi Discrete Multi

Chess without a clock Fully Strategic Sequential Static Discrete Multi

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obser Determi Episodic Static Discrete Agents
vable nistic
Chess with a clock Fully Strategic Sequential Semi Discrete Multi

Chess without a Fully Strategic Sequential Static Discrete Multi

clock
Poker

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obser Determi Episodic Static Discrete Agents
vable nistic
Chess with a clock Fully Strategic Sequential Semi Discrete Multi

Chess without a clock Fully Strategic Sequential Static Discrete Multi

Poker Partial Strategic Sequential Static Discrete Multi

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Observ Determini Episodic Static Discrete Agents
able stic
Chess with a clock Fully Strategic Sequential Semi Discrete Multi

Chess without a clock Fully Strategic Sequential Static Discrete Multi

Poker Partial Strategic Sequential Static Discrete Multi

Backgammon

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
stic al c e

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
stic al c e
Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
stic al c e
Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous
Medical diagnosis
Fully observable vs. partially observable
Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
stic al c e
Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous
Medical diagnosis Partia Stocha Episodic Stati Contin Single
l stic c uous
Fully observable vs. partially observable
Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
stic al c e
Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous
Medical diagnosis Partia Stocha Episodic Stati Contin Single
l stic c uous
Fully observable vs. partially observable
Deterministic vs. stochasticImage analysis
/ strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
Fully observable vs. stic al c e

partially observable Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous
Deterministic vs. Medical diagnosis Partia Stocha Episodic Stati Contin Single
stochastic / strategic l stic c uous
Episodic vs. sequential Image analysis Fully Determ Episodic Semi Discret Single
Static vs. dynamic inistic e

Discrete vs.
continuous
Single agent vs.
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
Fully observable vs. stic al c e

partially observable Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous
Deterministic vs. Medical diagnosis Partia Stocha Episodic Stati Contin Single
stochastic / strategic l stic c uous
Episodic vs. sequential Image analysis Fully Determ Episodic Semi Discret Single
Static vs. dynamic inistic e
Robot part picking
Discrete vs.
continuous
Single agent vs.
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e

Fully observable vs. Backgammon Fully Stocha Sequenti Stati Discret Multi
stic al c e
partially observable
Taxi driving Partia Stocha Sequenti Dyn Contin Multi
Deterministic vs. l stic al amic uous
stochastic / strategic Medical diagnosis Partia Stocha Episodic Stati Contin Single
Episodic vs. sequential l stic c uous
Static vs. dynamic Image analysis Fully Determ Episodic Semi Discret Single
inistic e
Discrete vs.
Robot part picking Fully Determ Episodic Semi Discret Single
continuous inistic e
Single agent vs.
multiagent
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
Fully observable vs. stic al c e

partially observable Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous
Deterministic vs. Medical diagnosis Partia Stocha Episodic Stati Contin Single
stochastic / strategic l stic c uous
Episodic vs. sequential Image analysis Fully Determ Episodic Semi Discret Single
Static vs. dynamic inistic e
Robot part picking Fully Determ Episodic Semi Discret Single
Discrete vs. inistic e
continuous
Interactive English
Single agent vs. tutor
 Environment Obse Determ Episodic Stati Discret Agent
rvabl inistic c e s
e
Chess with a clock Fully Strateg Sequenti Semi Discret Multi
ic al e
Chess without a Fully Strateg Sequenti Stati Discret Multi
clock ic al c e
Poker Partia Strateg Sequenti Stati Discret Multi
l ic al c e
Backgammon Fully Stocha Sequenti Stati Discret Multi
Fully observable vs. stic al c e

partially observable Taxi driving Partia Stocha Sequenti Dyn Contin Multi
l stic al amic uous
Deterministic vs. Medical diagnosis Partia Stocha Episodic Stati Contin Single
stochastic / strategic l stic c uous
Episodic vs. sequential Image analysis Fully Determ Episodic Semi Discret Single
Static vs. dynamic inistic e
Robot part picking Fully Determ Episodic Semi Discret Single
Discrete vs. inistic e
continuous
Interactive English Partia Stocha Sequenti Dyn Discret Multi
Single agent vs. tutor l stic al amic e
“THANK YOU”