CHAPTER 1:

Introduction to Artificial Intelligence

By: Getaneh T.

What is Intelligence?
Intelligence:
the capacity to learn and solve problems
(Websters dictionary)
in particular,
the ability to solve novel problems
the ability to act rationally
the ability to act like humans
Artificial Intelligence
build and understand intelligent entities or agents
2 main approaches: engineering versus
cognitive modeling

Whats involved in Intelligence?

Ability to interact with the real world

to perceive, understand, and act

e.g., speech recognition and understanding and synthesis
e.g., image understanding
e.g., ability to take actions, have an effect

Reasoning and Planning

modeling the external world, given input
solving new problems, planning, and making decisions
ability to deal with unexpected problems, uncertainties

Learning and Adaptation

we are continuously learning and adapting
our internal models are always being updated
e.g., a baby learning to categorize and recognize animals

Academic Disciplines relevant to AI

Philosophy

Logic, methods of reasoning, mind as physical

system, foundations of learning, language,
rationality.

Mathematics
Formal representation and proof, algorithms,
computation, (un)decidability, (in)tractability

Probability/Statistics

Economics

utility, decision theory, rational economic agents

Neuroscience

neurons as information processing units.

Psychology/
Cognitive Science

Computer
engineering

Control theory design systems that maximize an objective

function over time

Linguistics

modeling uncertainty, learning from data

how do people behave, perceive, process cognitive

information, represent knowledge.

building fast computers

knowledge representation, grammars

History of AI
1943: early beginnings

McCulloch & Pitts: Boolean circuit model of brain

1950: Turing

Turing's "Computing Machinery and Intelligence

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 interest

Newell and Simon: GPS, general problem solver

Gelertner: Geometry Theorem Prover
McCarthy: invention of LISP

History of AI
196673: Reality dawns

Realization that many AI problems are intractable

Limitations of existing neural network methods identified
Neural network research almost disappears

196985: Adding domain knowledge

Development of knowledge-based systems

Success of rule-based expert systems,
E.g., DENDRAL
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

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

HAL: from the movie 2001

2001: A Space Odyssey

classic science fiction movie from 1969

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?

Hal and AI
HALs Legacy: 2001s Computer as Dream and Reality
MIT Press, 1997, David Stork (ed.)
discusses
HAL as an intelligent computer
are the predictions for HAL realizable with AI today?

Consider what might be involved in building

a computer like Hal.
What are the components that might be useful?
Fast hardware?
Chess-playing at grandmaster level?
Speech interaction?
speech synthesis
speech recognition
speech understanding
Image recognition and understanding ?
Learning?
Planning and decision-making?

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!

Can Computers beat Humans at Chess?

Chess Playing is a classic AI problem
well-defined problem
very complex: difficult for humans to play well

3000
2800

Points Ratings

2600

Deep Blue

Human World Champion

2400

Deep Thought

2200
2000
1800

Ratings

1600
1400

1200
1966 1971
Conclusion:

1976

1981

1986

1991

1997

YES: todays computers can beat even the best human

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 dont: so they sound unnatural

Conclusion:
NO, for complete sentences
YES, for individual words

Can Computers Recognize Speech?

Speech Recognition:
mapping sounds from a microphone into a list of words
classic problem in AI, very difficult
Lets talk about how to wreck a nice beach
(I really said ________________________)

Recognizing single words from a small vocabulary

systems can do this with high accuracy (order of 99%)
e.g., directory inquiries
limited vocabulary (area codes, city names)
computer tries to recognize you first, if unsuccessful hands
you over to a human operator
saves millions of dollars a year for the phone companies

Recognizing human speech

(ctd.)

Recognizing normal speech is much more difficult

speech is continuous: where are the boundaries between words?
e.g., Johns 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

Conclusion:
NO, normal speech is too complex to accurately recognize
YES, for restricted problems (small vocabulary, single speaker)

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?

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: time the flies the way an arrow times the
flies
3. command: only time those flies which are like an arrow
4. time-flies are fond of arrows

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: time the flies the way an arrow times the
flies
3. command: only time those flies which are like an arrow
4. 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

Conclusion: NO, much of what we say is beyond the

capabilities of a computer to understand at present

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 90s it drove 98% of the way from Pittsburgh to
San Diego without any human assistance
machine learning allows computers to learn to do things.
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

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)

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

What makes planning hard?

the world is not predictable:
your flight is canceled or theres 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

Summary of State of AI Systems in Practice

Speech synthesis, recognition and understanding

very useful for limited vocabulary applications
unconstrained speech understanding is still too hard

Computer vision
works for constrained problems (hand-written zip-codes)
understanding real-world, natural scenes is still too hard

Learning
adaptive systems are used in many applications: have their limits

Planning and Reasoning

only works for constrained problems: e.g., chess
real-world is too complex for general systems

Overall:
many components of intelligent systems are doable
there are many interesting research problems remaining

Intelligent Agent
sensors
?

percepts
environment

agent
actuators

actions

Definition: An intelligent agent perceives its

environment via sensors and acts rationally
upon that environment with its actuators.

e.g., Humans

Sensors:
Eyes (vision), ears (hearing), skin (touch), tongue
(gustation), nose (olfaction), neuromuscular system
(proprioception)

Percepts:
At the lowest level electrical signals
After preprocessing objects in the visual field
(location, textures, colors, ), auditory streams
(pitch, loudness, direction),

Actuators: limbs, digits, eyes, tongue,

Actions: lift a finger, turn left, walk, run,
carry an object,

Notion of an Artificial
Agent
sensors

?
environment
agent
actuators

laser range
finder

sonars
touch sensors

Notion of an Artificial
Agent
sensors

?
environment
agent
actuators

Vacuum Cleaner World

Percepts: location and contents, e.g. [A, Dirty]

Actions: Left, Right, Suck, NoOp

Vacuum Agent Function

Percept Sequence
[A, Clean]
[A, Dirty]
[B, Clean]
[B, Dirty]
[A, Clean], [A,
Clean]
[A, Clean], [A, Dirty]

Action
Right
Suck
Left
Suck
Right
Suck
28

Rational Agent

What is rational depends on:

Performance measure - The performance
measure that defines the criterion of success
Environment - The agents prior knowledge of the
environment
Actuators - The actions that the agent can
perform
Sensors - The agents percept sequence to date

Well call all this the Task Environment

(PEAS)

Vacuum Agent PEAS

Performance Measure: minimize energy
consumption, maximize dirt pick up.
Making this precise: one point for each
clean square over lifetime of 1000 steps.
Environment: two squares, dirt
distribution unknown, assume actions are
deterministic and environment is static
(clean squares stay clean)
Actuators: Left, Right, Suck, NoOp
Sensors: agent can perceive its location
and whether location is dirty

Automated taxi driving

system
Performance Measure: Maintain safety, reach
destination, maximize profits (fuel, tire wear),
obey laws, provide passenger comfort,
Environment: U.S. urban streets, freeways,
traffic, weather, customers,
Actuators: Steer, accelerate, brake, horn,
speak/display,
Sensors: Video, sonar, speedometer,
odometer, engine sensors, keyboard input,
microphone, GPS,

Properties of Environments
Fully Observable/Partially Observable
If an agents sensors give it access to the complete state
of the environment needed to choose an action, the
environment is fully observable.
Such environments are convenient, since the agent is
freed from the task of keeping track of the changes in
the environment.
Deterministic
An environment is deterministic if the next state of the
environment is completely determined by the current
state of the environment and the action of the agent.
In a fully observable and deterministic environment, the
agent need not deal with uncertainty.

Properties of Environments
Static/Dynamic.
A static environment does not change while
the agent is thinking.
The passage of time as an agent deliberates is
irrelevant.
The agent doesnt need to observe the world
during deliberation.
Discrete/Continuous.
If the number of distinct percepts and actions
is limited, the environment is discrete,
otherwise it is continuous.

Some agent types

(0) Table-driven agents
use a percept sequence/action table in memory to find the next action.
They are implemented by a (large) lookup table.

(1) Simple reflex agents

are based on condition-action rules, implemented with an appropriate
production system. They are stateless devices which do not have memory
of past world states.

(2) Model-based reflex agents

have internal state, which is used to keep track of past states of the
world.

(3) Goal-based agents

are agents that, in addition to state information, have goal information
that describes desirable situations. Agents of this kind take future events
into consideration.

(4) Utility-based agents

base their decisions on classic axiomatic utility theory in order to act
rationally.

(0) Table-driven agents

Table lookup of percept-action pairs mapping from

every possible perceived state to the optimal action
for that state
Problems
Too big to generate and to store (Chess has about
10120 states, for example)
No knowledge of non-perceptual parts of the
current state
Not adaptive to changes in the environment;
requires entire table to be updated if changes occur
Looping: Cant make actions conditional on previous
actions/states

(1) Simple reflex agents

Rule-based reasoning to map from percepts to

optimal action; each rule handles a collection of
perceived states
Problems
Still usually too big to generate and to store
Still no knowledge of non-perceptual parts of
state
Still not adaptive to changes in the environment;
requires collection of rules to be updated if
changes occur
Still cant make actions conditional on previous
state

(1) Simple reflex agent

architecture

Simple Vacuum Reflex Agent

function Vacuum-Agent([location,status])
returns Action
if status = Dirty then return Suck
else if location = A then return Right
else if location = B then return Left

(2) Model-based reflex agents

Encode internal state of the world to

remember the past as contained in
earlier percepts.
Needed because sensors do not usually
give the entire state of the world at each
input, so perception of the environment
is captured over time. State is used to
encode different "world states" that
generate the same immediate percept.

(2)Model-based agent
architecture

(3) Goal-based agents

Choose actions so as to achieve a (given or

computed) goal.
A goal is a description of a desirable situation.
Keeping track of the current state is often not
enough need to add goals to decide which
situations are good
Deliberative instead of reactive.
May have to consider long sequences of
possible actions before deciding if goal is
achieved involves consideration of the future,
what will happen if I do...?

Example: Tracking a
Target

The robot must keep

the target in view
The targets trajectory
is not known in advance
The robot may not know
all the obstacles in
advance
Fast decision is required

robot

target

(3) Architecture for goalbased agent

(4) Utility-based agents

When there are multiple possible alternatives, how to

decide which one is best?
A goal specifies a crude distinction between a happy
and unhappy state, but often need a more general
performance measure that describes degree of
happiness.
Utility function U: State Reals indicating a
measure of success or happiness when at a given
state.
Allows decisions comparing choice between
conflicting goals, and choice between likelihood of
success and importance of goal (if achievement is
uncertain).

(4) Architecture for a

complete
utility-based agent

Summary: Agents
An agent perceives and acts in an environment, has an
architecture, and is implemented by an agent program.
Task environment PEAS (Performance, Environment,
Actuators, Sensors)
An ideal agent always chooses the action which maximizes its
expected performance, given its percept sequence so far.
An autonomous learning agent uses its own experience rather
than built-in knowledge of the environment by the designer.
An agent program maps from percept to action and updates
internal state.
Reflex agents respond immediately to percepts.
Goal-based agents act in order to achieve their goal(s).
Utility-based agents maximize their own utility function.

Representing knowledge is important for successful agent

design.
The most challenging environments are not fully observable,

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

AI Applications: Machine Translation

Language problems in international business

e.g., at a meeting of Japanese, Korean, Vietnamese and Swedish investors,
no common language
or: you are shipping your software manuals to 127 countries
solution; hire translators to translate
would be much cheaper if a machine could do this

How hard is automated translation

very difficult! e.g., English to Russian
The spirit is willing but the flesh is weak (English)
the vodka is good but the meat is rotten (Russian)
not only must the words be translated, but their meaning also!
is this problem AI-complete?

Nonetheless....
commercial systems can do a lot of the work very well (e.g.,restricted
vocabularies in software documentation)
algorithms which combine dictionaries, grammar models, etc.
Recent progress using black-box machine learning techniques

AI and Web Search

Whats involved in Intelligence? (again)

Perceiving, recognizing, understanding the real world
Reasoning and planning about the external world
Learning and adaptation

So what general principles should we use to achieve these

goals?

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

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?

Thinking humanly
Cognitive/Rational/Reasoning 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
Machines dont behave rationally
e.g., insurance
The reverse engineering is very hard to do
The brains hardware is very different to a computer program

Thinking rationally
Represent facts about the world via logic
Use logical inference as a basis for reasoning about these facts
Can be a very useful approach to AI
E.g., theorem-provers

Limitations
Does not account for an agents uncertainty about the world
E.g., difficult to couple to vision or speech systems
Has no way to represent goals, costs, etc (important aspects of
real-world environments)

Acting rationally
Decision theory/Economics
Set of future states of the world
Set of possible actions an agent can take
Utility = gain to an agent for each action/state pair
An agent acts rationally if it selects the action that maximizes its
utility
Or expected utility if there is uncertainty

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)

Summary of this chapter

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.

Rational agent view of AI

Reading: chapter 1 in text, Thrun paper, Stone lecture