Download Introduction to AI - Dr Shahriar Bijani

ARTIFICIAL INTELLIGENCE
INTRODUCTION TO ARTIFICIAL
INTELLIGENCE
Dr. Shahriar Bijani
Shahed University
Spring 2017
OUTLINE

What is AI?

A brief history

Predictions and Reality
Shahed University, Spring 2017
Course overview
Introduction to AI

2
COURSE OVERVIEW
Introduction to AI
 Introduction
Shahed University, Spring 2017
and Agents (chapters 1,2)
 Search (chapters 3,4,5,6)
 Logic (chapters 7,8,9)
 Knowledge Representation (chapter 10)
 Planning (chapters 11,12)
 Uncertainty (chapters 13,14)
 Learning (chapters 18,20)
 Natural Language Processing (chapter 22,23)
 Other Topics (Neural Nets, ….)
3
FOUND ON THE WEB …
Introduction to AI
AI is the reproduction of the methods of human
reasoning
or perception
Intelligent
 Using
computational models to simulate intelligent
behavior
(human) behavior and processes
Computer
 AI is the study of mental abilities through the use
computational methods

Shahed University, Spring 2017
Humans
4
Introduction to AI
WHAT IS AI?
Act like humans
Act rationally
Think like humans
Think rationally
Shahed University, Spring 2017
Discipline that systematizes and
automates intellectual tasks to create
machines that:
5
Introduction to AI
ACT LIKE HUMANS
 The





Shahed University, Spring 2017
goal of AI is to create computer systems
that perform functions that are assumed to
require intelligence when done by humans
  Methodology:
Take a task at which people are better, e.g.:
Prove a theorem
Play chess
Plan a surgical operation
Diagnose a disease
Navigate in a building
and make a computer do it
6
ACT LIKE HUMANS : TURING TEST


Alan Turing (1950) "Computing machinery and
intelligence":
"Can machines think?"  "Can machines behave
intelligently?"
Operational test for intelligent behavior: the simulation
game
The computer is asked questions by a human interviewer.
It passes the test if the interviewer or cannot tell whether
the responses come from a person
Shahed University, Spring 2017

Introduction to AI

7
ACT LIKE HUMANS : TURING TEST

Required capabilities: natural language
processing, knowledge representation, automated
reasoning, learning
Shahed University, Spring 2017

Introduction to AI

No physical interaction
total Turing Test, needs computer vision &
robotics
8
Think like humans
Think rationally
Shahed University, Spring 2017
Discipline that systematizes and
automates intellectual tasks to create
machines that:
Act like humans
Act rationally
Introduction to AI
WHAT IS AI?
12
THINKING HUMANLY: COGNITIVE

How the computer performs functions does matter
Comparison of the traces of the reasoning steps (cognitive
science)

1960s "cognitive revolution": information-processing psychology

Cognitive science: computer models (from AI) + experiments
from Psychology


Requires scientific theories of internal activities of the brain, by:
1) Predicting and testing behavior of human subjects (top-down)
or 2) Direct identification from neurological data (bottom-up)

Shahed University, Spring 2017

Introduction to AI
MODELING
Both approaches (roughly, Cognitive Science and Cognitive
Neuroscience) are now distinct from AI


But, do we want to duplicate human imperfections?
13
DISCOURSE ON THE METHOD, BY DESCARTES
(1598-1650)
Introduction to AI
Shahed University, Spring 2017
If there were machines which bore a resemblance to our
bodies and imitated our actions as closely as possible for
all practical purposes, we should still have two very
certain means of recognizing that they were not real men.
The first is that they could never use words, or put
together signs, as we do in order to declare our thoughts
to others… Secondly, even though some machines might
do some things as well as we do them, or perhaps even
better, they would inevitably fail in others, which would
reveal that they are acting not from understanding, …
14
DISCOURSE ON THE METHOD, BY DESCARTES
(1598-1650)
Introduction to AI
Shahed University, Spring 2017
If there were machines which bore a resemblance to our
bodies and imitated our actions as closely as possible for
all practical purposes, we should still have two very
certain means of recognizing that they were not real men.
The first is that they could never use words, or put
together signs, as we do in order to declare our thoughts
to others… Secondly, even though some machines might
do some things as well as we do them, or perhaps even
better, they would inevitably fail in others, which would
reveal that they are acting not from understanding, …
15
DISCOURSE ON THE METHOD, BY DESCARTES
(1598-1650)
Introduction to AI
Shahed University, Spring 2017
If there were machines which bore a resemblance to our
bodies and imitated our actions as closely as possible for
all practical purposes, we should still have two very
certain means of recognizing that they were not real men.
The first is that they could never use words, or put
together signs, as we do in order to declare our thoughts
to others… Secondly, even though some machines might
do some things as well as we do them, or perhaps even
better, they would inevitably fail in others, which would
reveal that they are acting not from understanding, …
16
Think like humans
Think rationally
Shahed University, Spring 2017
Discipline that systematizes and
automates intellectual tasks to create
machines that:
Act like humans
Act rationally
Introduction to AI
WHAT IS AI?
17
THINKING RATIONALLY: "LAWS OF
THOUGHT"


1.
2.
It is not easy to state informal knowledge in the formal
terms required by logical notation (particularly when it
is less than 100% certain).
There is a big difference between being able to solve a
problem "in principle" and doing so in practice.
Shahed University, Spring 2017

Aristotle: what are correct arguments/thought
processes?
Logicians developed various forms of logic:
notation and rules of derivation for thoughts;
By 1965, programs existed that could solve any
problem described in logical notation.
Problems:
Introduction to AI

18
Think like humans
Think rationally
Shahed University, Spring 2017
Discipline that systematizes and
automates intellectual tasks to create
machines that:
Act like humans
Act rationally
Introduction to AI
WHAT IS AI?
19
ACTING RATIONALLY: RATIONAL
AGENT
Introduction to AI
Shahed University, Spring 2017
Rational behavior: doing the right thing
 The right thing: that which is expected to maximize
goal achievement, given the available information
 Doesn't necessarily involve thinking – e.g., blinking
reflex – but thinking should be in the service of
rational action

20
RATIONAL AGENTS
 For
any given class of environments and
tasks, we seek the agent (or class of agents)
with the best performance
 computational limitations make perfect
rationality unachievable  design best
program for given machine resources
Shahed University, Spring 2017
agent is an entity that perceives and acts
 This course is about designing rational
agents
 Abstractly, an agent is a function from
percept histories to actions:
[f: P*  A]
Introduction to AI
 An
21
AI PREHISTORY
Mathematics
algorithms,
(in)tractability,



Economics
Neuroscience
Psychology

Computer
engineering
Control theory

Linguistics

Logic, methods of reasoning, mind as
system foundations of learning, language,
rationality
Formal representation and proof
computation, (un)decidability,
probability
utility, decision theory
physical substrate for mental activity
phenomena of perception and motor control,
experimental techniques
building fast computers
design systems that maximize an objective
function over time
knowledge representation, grammar
Shahed University, Spring 2017

Philosophy
physical
Introduction to AI

25
SHORT HISTORY OF AI











1965
1966—73
1969—79
1980-1986-1987-1995-2003--
McCulloch & Pitts: Boolean circuit model of brain
Turing's "Computing Machinery and Intelligence"
Dartmouth meeting: "Artificial Intelligence" adopted
Look, Ma, no hands!
Early AI programs, including Samuel's checkers
program, Newell & Simon's Logic Theorist,
Gelernter's Geometry Engine
Robinson's complete algorithm for logical reasoning
AI discovers computational complexity
Neural network research almost disappears
Early development of knowledge-based systems
AI becomes an industry
Neural networks return to popularity
AI becomes a science
The emergence of intelligent agents
26
Human-level AI back on the agenda
Shahed University, Spring 2017

1943
1950
1956
1952—69
1950s
Introduction to AI

A SHORT HISTORY OF AI

1940-1950: Early days



1943: McCulloch & Pitts: Boolean circuit model of brain
1950: Turing's “Computing Machinery and Intelligence”
1950—70: Excitement: Look, Ma, no hands!
1950s: Early AI programs, including Samuel's checkers program,
Newell & Simon's Logic Theorist, Gelernter's Geometry Engine
 1956: Dartmouth meeting: “Artificial Intelligence” adopted
 1965: Robinson's complete algorithm for logical reasoning


1970—90: Knowledge-based approaches




1990—: Statistical approaches




1969—79: Early development of knowledge-based systems
1980—88: Expert systems industry booms
1988—93: Expert systems industry collapse: “AI Winter”
Reappearance of probability, focus on uncertainty
General increase in technical depth
Agents and learning systems… “AI Spring”?
2000—: Human-level AI back on the agenda
A BRIEF HISTORY




General problem solving (GPS)
Theorem proving
Games
Formal calculus
Shahed University, Spring 2017
The name “Artificial Intelligence” is
coined.
Early period (50’s to late 60’s):
Basic principles and generality
Introduction to AI
 1956:
28
Birth of AI occurred when Marvin Minsky & John McCarthy
organized the Dartmouth Conference in 1956

brought together researchers interested in "intelligent machines"
for next 20 years, all advances in AI were by following

Minsky (MIT), McCarthy (MIT/Stanford), Newell & Simon (Carnegie),…
John McCarthy
Marvin Minsky
Shahed University, Spring 2017

Introduction to AI
A BRIEF HISTORY :THE ORIGINS OF AI
29
Shahed University, Spring 2017
1969-1971: Shakey the
robot (Fikes, Hart, Nilsson)
 Logic-based planning
(STRIPS)
 Motion planning (visibility
graph)
 Inductive learning
(PLANEX)
 Computer vision

Introduction to AI
A BRIEF HISTORY
30
A BRIEF HISTORY
period (late 60’s to mid


Focus on narrow tasks requiring expertise
Encoding of expertise into rules, such as:
If A car has
▪ off-highway tires and
▪ 4-wheel drive and
▪ high ground clearance
Then the car can traverse difficult terrain (0.8)



Knowledge engineering
Japanese 5th generation computer project
CYC system
Shahed University, Spring 2017
80’s):
Introduction to AI
 Knowledge-is-Power
31
A BRIEF HISTORY
becomes an industry (80’s – present):
Shahed University, Spring 2017
Expert systems: Digital Equipment, Teknowledge,
Intellicorp, Du Pont, oil industry, …
 Lisp machines: LMI, Symbolics, …
 Constraint programming: ILOG
 Robotics: Adept, Fanuc, ABB, Sony, Honda,
iRobot, Evolution Robotics
 Voice processing
 Video games
 Fraud detection, image analysis, medical
diagnosis, …

Introduction to AI
 AI
32
A BRIEF HISTORY
Introduction to AI
Shahed University, Spring 2017
The return of neural networks, genetic algorithms, and
artificial life (80’s – 90’s)
 Increased connection with economics, probabilistic
modeling, and control theory (90’s – present)
- AI is less philosophical, more technical
- AI is a major source of computational techniques for
complex systems

33
PREDICTIONS AND REALITY … (1/3)
Shahed University, Spring 2017
the 60’s, a famous AI professor from MIT
said: “At the end of the summer, we will have
developed an electronic eye”
 Up to now, there is still no general computer
vision system capable of understanding
complex dynamic scenes
 But computer systems routinely perform road
traffic monitoring, facial recognition, medical
image analysis, part inspection, motion
capture, …
Introduction to AI
 In
34
PREDICTIONS AND REALITY … (2/3)
 This
prediction became true in 1998
 AI techniques (search, planning,
probabilistic reasoning) are used in many
video games
Shahed University, Spring 2017
1958, Herbert Simon (CMU) predicted
that within 10 years a computer would be
Chess champion
Introduction to AI
 In
35

Shahed University, Spring 2017
In the 70’s, many believed that
computer-controlled robots would
soon be everywhere from
manufacturing plants to home
Introduction to AI
PREDICTIONS AND REALITY … (3/3)
36
Shahed University, Spring 2017
In the 70’s, many believed that
computer-controlled robots would
soon be everywhere from
manufacturing plants to home
 Today, some industries
(automobile, electronics) are
highly robotized, but home robots
are still a thing of the future

Introduction to AI
PREDICTIONS AND REALITY … (3/3)
37
Shahed University, Spring 2017
In the 70’s, many believed that
computer-controlled robots would
soon be everywhere from
manufacturing plants to home
 Today, some industries
(automobile, electronics) are
highly robotized, but home robots
are still a thing of the future
 But robots have rolled (are rolling)
on Mars, fly autonomously,

Introduction to AI
PREDICTIONS AND REALITY … (3/3)
38
Introduction to AI
Shahed University, Spring 2017
39
Shahed University, Spring 2017
In the 70’s, many believed that
computer-controlled robots would
soon be everywhere from
manufacturing plants to home
 Today, some industries
(automobile, electronics) are
highly robotized, but home robots
are still a thing of the future
 But robots have rolled (are rolling)
on Mars, fly autonomously, while
others perform brain and heart
surgery …

Introduction to AI
PREDICTIONS AND REALITY … (3/3)
40
(http://world.honda.com/news/2001/c011112.html)
Shahed University, Spring 2017
In the 70’s, many believed that
computer-controlled robots would
soon be everywhere from
manufacturing plants to home
 Today, some industries
(automobile, electronics) are
highly robotized, but home robots
are still a thing of the future
 But robots have rolled (are rolling)
on Mars, fly autonomously, while
others perform brain and heart
surgery …
 and humanoid robots are
available for rent

Introduction to AI
PREDICTIONS AND REALITY … (3/3)
41
NATURAL LANGUAGE

Speech technologies (e.g. Siri)




Automatic speech recognition (ASR)
Text-to-speech synthesis (TTS)
Dialog systems
Language processing technologies


Question answering
Machine translation


Web search
Text classification, spam filtering, etc…
VISION (PERCEPTION)
 Object and face recognition
 Scene segmentation
 Image classification
Demo1: VISION – lec_1_t2_video.flv
Images from Erik Sudderth (left), wikipedia (right)
Demo2: VISION – lec_1_obj_rec_0.mpg
Demo 1: ROBOTICS – soccer.avi
Demo 2: ROBOTICS – soccer2.avi
Demo 3: ROBOTICS – gcar.avi
ROBOTICS

Robotics




Technologies





Part mech. eng.
Part AI
Reality much
harder than
simulations!
Vehicles
Rescue
Soccer!
Lots of automation…
In this class:



We ignore mechanical aspects
Methods for planning
Methods for control
Images from UC Berkeley, Boston Dynamics, RoboCup, Google
Demo 4: ROBOTICS – laundry.avi
Demo 5: ROBOTICS – petman.avi
LOGIC

Logical systems
Theorem provers
 NASA fault diagnosis
 Question answering


Methods:
Deduction systems
 Constraint satisfaction
 Satisfiability solvers (huge
advances!)

Image from Bart Selman
GAME PLAYING

Classic Moment: May, '97: Deep Blue vs. Kasparov






Open question:



First match won against world champion
“Intelligent creative” play
200 million board positions per second
Humans understood 99.9 of Deep Blue's moves
Can do about the same now with a PC cluster
How does human cognition deal with the
search space explosion of chess?
Or: how can humans compete with computers at all??
1996: Kasparov Beats Deep Blue
“I could feel --- I could smell --- a new kind of intelligence across the table.”

1997: Deep Blue Beats Kasparov
“Deep Blue hasn't proven anything.”

Huge game-playing advances recently, e.g. in Go!
Text from Bart Selman, image from IBM’s Deep Blue
pages
DECISION MAKING

Applied AI involves many kinds of
automation
Scheduling, e.g. airline routing, military
 Route planning, e.g. Google maps
 Medical diagnosis
 Web search engines
 Spam classifiers
 Automated help desks
 Fraud detection
 Product recommendations
 … Lots more!

DESIGNING RATIONAL AGENTS

An agent is an entity that perceives and acts.

A rational agent selects actions that maximize
its (expected) utility.

Characteristics of the percepts, environment,
and action space dictate techniques for
selecting rational actions
Sensors
Percepts
?
Actuators
Actions
Environment
This course is about:
 General AI techniques for a variety of
problem types
 Learning to recognize when and how a new
problem can be solved with an existing
technique
Agent

PAC-MAN AS AN AGENT
Agent
Sensors
Environment
Percepts
?
Actuators
Actions
Pac-Man is a registered trademark of Namco-Bandai Games, used here for educational purposes
Demo1: pacman-l1.mp4 or L1D2
54