Department of Computer Science

Introduction to Artificial Intelligence

COSC3112
 Course
⚫ Course code:
Detail
COSC3112
⚫ Credit hours: 3 ECTS:
5
⚫ Contact hrs: 2
⚫ Lab hrs: 3
⚫ Tutorial hrs: 2
⚫ Prerequisite:CoSc2092-Data Structures and
Algorithms,
STAT2015- Probability and Statistics
⚫ Course category: compulsory
⚫ Year: IIII
Semester: I

2
 Course
⚫ T h e purpose of this course is to give students
Description
an understanding of Artifi cial Intelligence
methodologies, techniques, tools and results.
⚫ Students will use py th on pr og r ammi n g
language to demonstrate laboratory
exercises.
⚫ Students will learn the theoretical and
conceptual components
of this discipline and fi rm u p their understanding b y
using AI and Expert System tools in laboratory
sessions, projects and h o m e assignments.

3
 Course
At the end o f this course the students will be able
objectives
to:
⚫ Understand reasoning, knowledge representation and
learning
techniques of artifi cial intelligence
⚫ Evaluate the strengths and weaknesses of these
techniques and their applicability to diff erent tasks
⚫ Assess the role of AI in gaining insight into
intelligence and perception
⚫ Kn ow classical examples of artifi cial intelligence
⚫ Kn ow characteristics of programs that can be
considered
"intelligent"

4 ⚫ Understand the use of heuristics in search

 Course
⚫ Kn ow a variety of ways to represent and retrieve
objectives
knowledge and information
⚫ Kn ow the fundamentals of artifi cial intelligence
programming techniques in a m od e r n programming
language
⚫ Consider ideas and issues associated with social
technical, and
ethical uses of machines that involve artifi cial
intelligence
⚫ Introduce students for powerful learning algorithms
and their applications.
⚫ Letting students to develop simple AI powered
applications
5 either in robotics, N L P or games.
 Course
Outline
Topic Contents
Introduction to Objectives/Goals of AI, Types of AI(General and Specific AI), Approaches to AI
AI(3 hrs) – making computer: Think like a human ( Thinking humanly),Act like a human
(Acting humanly), Think rationally (Thinking rationally) & Act rationally (Acting
rationally). The Foundations of AI, Bits of History and the State of the Art,
Proposing and evaluating Application of AI

Intelligent Agents Foundation of Agents, Agents and Environments, Acting of Intelligent Agents
(4 hrs) (Rationality), Structure of Intelligent Agents: Agent Types, Simple reflex
agent, Model-based reflex agent, Goal-based agent, Utility-based agent. Multi
agent systems, Learning agent

Searching and Solving Problems by Searching and planning, Constraint Satisfaction Problem,
Planning (6 hrs) Problem Solving Agents, Problem spaces and search, Knowledge and
rationality, Heuristic search strategies, Search and optimization (gradient
descent), Adversarial search, Planning and scheduling, Avoiding Repeated
States, Dynamic game theory

Knowledge Logic and Inference, Logical Agents, Propositional Logic, Predicate (First-
Representation Order) Logic, Inference in First-Order Logic, Knowledge Representation,
and Reasoning (8 Knowledge Reasoning, Bayesian reasoning, Probabilistic reasoning, Temporal
hrs) reasoning, Knowledge-based Systems, Case study: Medical diagnosis
6
 Course Outline…
Machine Learning Knowledge in Learning, Learning Probabilistic Models, Supervised learning:
Basics (3 hrs) Linear classification models, Probabilistic models., Unsupervised learning:
Clustering models, Reinforcement learning, Deep Learning: Neural networks and
back- propagation, Convolution neural networks, Recurrent neural networks and
LSTMs

Natural Language Intro to Natural Language Processing, Machine learning Application in NLP,
Processing (NLP) Natural language interaction, Computer vision and Image processing, Case
Basics (3 hrs) study: Sentiment Analysis, speech recognition, Chatbot

Robotic Sensing Introduction to robotics: Sensing, Manipulation, Human-robot interaction.

and Manipulation Navigation and path planning: Autonomous robotic systems
(3 hrs)

Ethical and Legal Privacy, Bias, AI and the future of work, Appropriate uses of AI
Considerations in
AI (2 hrs)

7
 Assessment methods
⚫ This course is assessed b y written
exams, lab assignments, reports and
presentations of assignments.
⚫ Assessment Breakdown:
⚫ Assignment/quizzes 10 %
⚫ M id semester examination

⚫
20%
Project ` 20%
Final examination 50%

8
 Reading
⚫ Material
Text Books:
⚫ Russell, S. and P. Norvig (1995) Artifi cial
Intelligence: A M ode r n Approach Prentice-Hall
⚫ References:
⚫ Luger, G. (2002) Artifi cial Intelligence, 4th ed.
Addison- Wesley.
⚫ Bratko, Ivan (1990) P R O L O G Programming for
Artifi cial Intelligence, 2nd ed. Addison-Wesley,
1990
⚫ Winston, P.H. (1992) Artifi cial Intelligence Addison-
Wesley. Ginsberg, M.L. (1993) Essentials of Artifi cial
Intelligence. Morgan Kaufman.

9
Topic 1: Introduction to AI
 Introduction to Artificial
Intelligence
 O v e r v i e w of AI
 Objectives/Goals of AI
 T y p e s of AI(General and Specifi c AI)
 Approaches to AI – making computer:
 Think like a human ( Thinking
humanly)
 Act like a human (Acting humanly)
 Think rationally (Thinking rationally)
 Act rationally (Acting rationally)
 T h e Foundations of AI
 Bits of History and the State of the Art
 Proposing and evaluating Application
of AI
11
 Overview of
AIWe
⚫ call ourselves H o m o sapiens—m a n the w i s e —
because our
intelligence is so important to us.

⚫ For thousands of years, we have tried to understand

h ow w e think; that is, h ow a m e r e handful of matter can
perceive, understand, predict, and manipulate a world
far larger and m o r e complicated than itself.
⚫ T h e fi eld of artificial intelligence, or AI, goes further
still: ti attempts not just to understand but also to build
intelligent entities.
⚫ AI is one of the newest fi elds in science and
engineering. Wo r k started in earnest soon after Wor l d
12 War II, and the n am e itself was coined in 1956.
 Overview of
AIAI
⚫ currently encompasses a huge variety of
subfi elds, ranging
f r o m the general (learning and perception) to the
specifi c,
such as playing chess, proving mathematical
theorems, writing poetry, driving a car on a
crowded street, and diagnosing diseases.
⚫ AI is relevant to any intellectual task; it is truly
a universal
fi eld.

13
 Intelligence
⚫ Intelligence is the computational part of the ability
to achieve
goals in the world.

⚫ Varying kinds and degrees of intelligence occur

in people, m a n y animals and some machines.
⚫ Intelligence is the capability of observing,
learning,
remembering, reasoning and acting.
⚫ AI attempts to develop intelligent agents.
Characteristics of Intelligent system
⚫ Use vast amount of knowledge
⚫ Learn f r o m experience and adopt to changing
environment
⚫ Interact with human using language and speech
⚫ Respond in real time
1
4
⚫ Tolerate error and ambiguity in communication
 Artificial Intelligence
⚫ It is the science and engineering of making
intelligent
machines, especially intelligent computer programs.

⚫ It is related to the similar task of using

computers to understand h u m a n intelligence, but
AI does not have to confi ne itself to methods that
are biologically observable.
⚫ Isn't there a solid definition of intelligence that
doesn't
depend on relating it to human intelligence?
⚫ Not yet. T h e problem is that we cannot yet
characterize in general what kinds of computational
procedures we want to call intelligent. We understand
1 some of the mechanisms of
5
 Artificial Intelligence
⚫ T h e concern of AI is to develop computer based
system that
behave like h u m a n and emulate the reasoning power
of
humans in order to do tasks that require h u m a n
intelligence.
Which task requires intelligence?
⚫ C o m p l e x arithmetic operations
⚫ For instance, Solving 220 * 350?

⚫ Mundane tasks: all tasks routinely done b y all of us

in our day- to-day activities:
⚫ Example, Natural language understanding; face
recognition;
planning; robotics, …

1 ⚫ Expert tasks: which require specialists knowledge

6
⚫ Example, Medical diagnosis; computer
 Artificial Intelligence
⚫ Artifi cial intelligence, or AI, is the fi eld that studies
the
synthesis and analysis of computational agents that
act
intelligently. Consider each part of this defi nition.

⚫ An agent is something that acts in an

environment; it does something.
⚫ Agents include worms, dogs, thermostats,
airplanes, robots,
humans, companies, and countries.
⚫ An agent is judged solely b y h ow it acts. Agents
that have the same eff ect in the world are equally
good.
17
 Artificial Intelligence
⚫ Intelligence is a matter of degree. T h e aspects that go
into an
agent acting intelligently include:

⚫ what it does is appropriate for its

circumstances, its goals, and its perceptual and
computational limitations
⚫ it takes into account the short-term and
long-term consequences of its actions,
including the eff ects on society and the
environment
⚫ it learns f r o m experience
⚫ it is fl exible to changing environments and
changing goals.
18
 Computational
Agent
⚫ A computational agent is an agent whose decisions
about its
actions can be explained in terms of computation.

⚫ That is, the decision can be broken d own into

primitive operations that can be implemented in a
physical device.
⚫ This computation can take m a n y forms. In
humans, this computation is carried out in
“wetware”; in computers it is carried out in
“hardware.”
⚫ Although there are some agents that are arguably
not computational, such as the wind and rain eroding
19 a landscape,
 Computational
Agent
⚫ All agents are limited. N o agent is omniscient (all
knowing) or
omnipotent (can d o anything).

⚫ Agents can only observe everything in very

specialized and constrained domains.
⚫ Agents have fi nite m e m o r y.
⚫ Agents in the real world d o not have unlimited
time to act.

20
 Objectives/Goals of AI
⚫ T h e central scientifi c goal of AI is to understand the
principles
that make intelligent behavior possible in natural or
artifi cial
systems. This is done by
⚫ the analysis o f natural and artifi cial agents

⚫ formulating and testing hypotheses about what it

takes to construct intelligent agents
⚫ designing, building, and experimenting with
computational systems that
p e r f or m tasks c o m m o n l y viewed as requiring intelligence.

⚫ As part o f science, researchers build empirical

systems to test hypotheses or to explore the space o f
possible designs.
2 ⚫ These are distinct f r o m applications that are built to
1 be useful for
Objectives/Goals of AI
⚫ T h e central engineering goal o f AI is the design
and synthesis of agents that act intelligently, which leads
to useful artifacts.
⚫ Building general intelligence isn’t the only goal o f AI
researchers.
⚫ T h e aim o f intelligence augmentation is to
augment human intelligence and creativity.
⚫A diagnostic agent helps medical practitioners
m a k e better decisions, a
search engine augments h u m a n m e m o r y, and natural
language translation systems help people communicate.
⚫ AI systems are often in h u m a n - in-the-loop m ode ,
where humans
and agents work together to solve problems.
⚫ Sometimes the actions of artifi cial agents are to give
 Types of AI(General
and Specific AI)
⚫ AI can generally be categorized into two types:
narrow (Special- purpose or weak) AI and general (or
strong) AI.
⚫ General-purpose AI like the robots o f science fi ction is
incredibly hard
⚫ H u m a n brain appears to have lots of special and
general functions, integrated in som e amazing w a y that w e
really d o not understand at all (yet)
⚫ T h e strong AI view holds that it is possible to
create intelligent machines that can really reason and
solve problems.
⚫ Such machines are considered to be conscious and
self-aware, can
security needs. think about problems and work out
independently
23
⚫ optimal
It can be regarded as a new civilization in a
solutions
 Types of AI(General
and Specific AI)
⚫ Special-purpose AI is m o r e doable (nontrivial)
⚫ E.g., chess/poker playing programs, logistics
planning,
automated translation, voice recognition, web
search, data mining, medical diagnosis, keeping a
car on the road, … …
……
⚫ T h e weak AI view holds that intelligent machines
cannot
really reason and solve problems.
⚫ These machines only look intelligent, but do
not have real intelligence or self-awareness.

24
 Strong AI vs Weak
AI
⚫ Strong AI argues that it is possible that one day a
computer will be invented which can be called a m i n d in
its fullest sense.
⚫ Strong AI aims to create an agent that can replicate
humans intelligence completely; i.e., it can think, reason,
imagine, etc., & d o all the things that are currently associated
with the h u m a n brain.
⚫ We a k AI, o n the other hand, argue that computers can
only
appear to think & are not actually conscious in the
same w a y as h u m a n brains are.
⚫ T h e weak AI position holds that AI should try to
develop systems which have facets of intelligence, but the
objective is not to build a completely sentient/conscious
25
entity.
 Strong AI vs Weak
AI
⚫ A k e y counter o f AI is to achieve a superhuman
level in challenging fi elds through self-learning
without any prior
knowledge.
⚫ T h e followers of strong AI believe that b y giving a computer

program suff icient

processing power, and b y providing it with enough intelligence,
one can create a
computer that can literally think and is conscious in the same way that a
huma n is conscious.
⚫ Strong AI can compete with humans in all aspects.
⚫ Therefore, it aims to enable robots to implement
human-like capabilities in all aspects rather than a
specifi c fi eld.
⚫ Strong AI can think, make plans, solve problems, per for m
naturally
26 abstract thinking, understand
occur(??).
complex concepts, quickly learn, and learn f r o m experience.
 Strong AI vs Weak
AIN o w w e are in the weak AI phase.
⚫
⚫ Weak AI, in contrast, is simply the view that intelligent behavior can be modeled and used

b y computers
to solve compl ex problems. This point of view argues that just because a computer behaves
intelligently
does not prove that it is actually intelligent in the way that a human is.

⚫ T h e emergence of weak AI alleviates human intellectual

labor, similar to advanced bionics.
⚫ Both AlphaGo and robots that can write press releases and
novels fall
in the weak AI phase because they are better than humans
only in
some ways.

⚫ T h e roles of data and computing power are self-evident in

the era of weak AI, and promote the commercialization of AI.
⚫ In the era of strong AI, these two factors are still critical.
27 ⚫ humans
At the same time, the research
to enter the era of
on quantum computing b y
 Strong AI vs Weak
AI AI
Weak Strong AI
Limited to perform specific tasks Perform intelligent human-level
activities
Programmed for fixed function Have the ability to learn, think, and
perform new activities like humans

It doesn’t have any consciousness It poses creativity, common sense,

or awareness of its own. and logic like humans.

They have a goal to complete a They have a goal to solve problems

task with creative and accurate at a faster pace.
solutions.
Examples of weak AI include Alexa, There are no real examples of
Siri, and Google Assistant. strong AI because it is a
hypothetical theory. Some fictional
examples are Wall-E and Big Hero
28
6.
 Approaches to AI –
computer:
making
⚫ AI is found on the premise
⚫ T h e workings of human mi n d
that: can be explained in
terms of
computation,
and
⚫ reasoning
computers rules.
can do the right thing given correct
⚫ Intelligence
premises andis:
⚫ “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
⚫ Views of AI fall into four categories:
Thinking humanly Thinking rationally
Acting humanly Acting rationally

29
 Approaches to AI – making computer:

30
 Thinking humanly:
The Cognitive
Modeling
Reasons like humans do
⚫

Programs that behave like humans

⚫

⚫ Requires understanding o f the internal

activities o f the brain
⚫ see h o w humans behave in certain
situations and see if y o u could m a k e
computers behave in that same way.
Example. write a program that plays chess.
⚫ Instead o f making the best possible
chess-playing program, y o u would m a k e
o n e that play chess like people do.

31
 Acting humanly: The
Turing Test
Can machines act like h u m a n do? Can machines
behave
intelligently?
⚫ Turing Test: Operational test for intelligent behavior
⚫ do experiments on the ability to achieve
human-level performance,
⚫ Acting like humans requires AI programs to
interact with
people
⚫ Suggested major components of AI include:
knowledge, reasoning, language understanding,
learning

32
 Thinking Rationally: The Laws
of Thought
⚫ A system is rational if it thinks/does the right thing
through
correct reasoning.

⚫ Aristotle: provided the correct arguments/thought

structures that always gave correct conclusions given
correct premises.
⚫ Belay is a man; all m e n are mortal; therefore
Belay is
mortal
⚫ These Laws of thought governed the
operation of the m i n d and initiated the fi eld of
Logic.

33
 Acting rationally: The rational
agent
⚫ Doing the right thing so as to achieve one’s goal,
given one’s
beliefs.

⚫ AI is the study and construction of rational agents

(an agent that perceives and acts)
⚫ Rational action requires the ability to represent
knowledge
and reason with it so as to reach good decision.
⚫ Learning for better understanding of h ow the
world works

34
 The Foundations of
AIAI is Interdisciplinary
⚫
⚫ AI is generally associated with C o m p u t e r
Science, but it
has m a n y important links with other fi elds such
as:
⚫ Mathematics,
⚫ Biology,
⚫ Economics,
⚫ Cognition,
⚫ Psychology,
⚫ Philosophy and
⚫ Neuroscience.

35
 Philosophy
⚫ Can formal rules be used to draw valid conclusions?
⚫ How does the mind arise from a physical brain?
⚫ Where does knowledge come from?
⚫ How does knowledge lead to action?
⚫ Descartes was a proponent o f dualism. He held that
there is a part o f the h u m a n m i n d (or soul or spirit) that is
outside o f nature,
exempt f r o m physical laws. Animals, o n the other hand,
did not possess this dual quality; they could be treated
as machines.
⚫ A n alternative to dualism is materialism, which holds
that the brain’s operation according to the laws o f
physics constitutes the
36
mind. Free will is simply the w a y that the perception o f
 Philosophy
⚫ T h e empiricism is characterized b y a dictum o f John
Locke (1632–1704): “Nothing is in the understanding,
which was not first
in the senses.”

⚫ T h e logical positivism holds that all knowledge can

be characterized b y logical theories connected,
ultimately, to observation sentences that correspond
to sensory inputs; thus
logical positivism combines rationalism and
empiricism.

⚫ T h e confirmation theory attempted to analyze the

acquisition of knowledge f r o m experience b y quantifying
the degree o f belief that should be assigned to logical
37
sentences based o n their
 Philosophy
⚫ Utilitarianism: that rational decision making based on
maximizing utility should apply to all spheres o f h u m a n
activity,
including public policy decisions m a d e o n behalf o f
m a n y individuals. Utilitarianism is a specifi c kind o f
consequentialism: the idea that what is right and wrong is
determined b y the expected outcomes o f an action.
⚫ In contrast, a theory o f rule-based or deontological
ethics, in which “doing the right thing” is determined not
b y outcomes but b y universal social laws that govern
allowable actions, such as “don’t lie” or “don’t kill.” M a n y
m o d e r n AI systems adopt exactly
38 this approach.
 Mathematics
⚫ What are the formal rules to draw valid conclusions?
⚫ What can be computed?
⚫ How do we reason with uncertain information?
⚫ T h e theory of probability can be seen as generalizing
logic to situations with uncertain information— a
consideration of great importance for AI. T h e formalization
of probability, combi ned with
the availability of data, led to the emergence of statistics as
a fi eld.

⚫ T h e history of computation is as old as the history of

numbers, but the fi rst nontrivial algorithm is thought to be
Euclid’s algorithm for computing greatest c o m m o n divisors.
T h e incompleteness theorem showed that in any formal
theory as strong as Peano arithmetic (the
39 elementary theory of natural numbers), there are
 Mathematics
⚫ Alan Turing tried to characterize exactly which functions
are
computable — capable of being computed b y an eff ective
procedure.
For example, no machine can tell in general whether a given
program will return an answer on a given input or run
forever.

⚫ Although computability is important to an

understanding of computation, the notion of tractability
has had an even greater
impact on AI. A problem is called intractable if the time
required to solve instances of the problem grows
exponentially with the size of the instances.
⚫ T h e theory of NP-completeness provides a basis for
analyzing the
40
tractability of problems: any problem class to which the
 Economics
⚫ How should we make decisions in accordance with our
preferences?
⚫ How should we do this when others may not go along?
⚫ How should we do this when the payoff may be far in the
future?
⚫ Decision theory, which combines probability theory with
utility theory, provides a formal and complete framework for
individual decisions (economic or otherwise) made under
uncertainty—that is, in
cases where probabilistic descriptions appropriately
capture the decision maker’s environment.
⚫ Models based on satisficing—making decisions that are
“good enough,” rather than laboriously calculating an
optimal decision— gave a better description of actual
41 human behavior.
 Neuroscienc
e
⚫
⚫
How do brains process information?
Neuroscience is the study of the nervous system,
particularly the
brain. A collection of simple cells can lead to thought,
action, and consciousness.
⚫ Even with a computer of virtually unlimited capacity, we
still require further conceptual breakthroughs in our
understanding of
intelligence.

42
 Psychology
⚫ How do humans and animals think and act?
⚫ Wundt insisted on carefully controlled experiments in
which his
workers would per for m a perceptual or associative task
while introspecting on their thought processes. T h e
behaviorism m o v e m e n t rejected any theory involving
mental processes on the grounds that introspection could
not provide reliable evidence.
⚫ Cognitive psychology views the brain as an information-
processing device. T h r e e k ey steps of a knowledge-based
agent: (1) the stimulus must be translated into an internal
representation, (2) the representation is manipulated b y
cognitive processes to derive new internal representations,
and (3) these are in turn retranslated back
43
into action.
 Computer engineering
⚫ How can we build an efficient computer?

⚫ Moore’s law states that performance doubled every

18 months.
⚫ Quantum computing holds out the promise of far
greater accelerations for some important subclasses
of AI algorithms.

44
 Control theory and
cybernetics
⚫ How can artifacts operate under their own control?

⚫ Mode r n control theory, especially the branch known as

stochastic optimal control, has as its goal the design of
systems that maxi mi ze a cost function over time.

45
 Linguistics
⚫ How does language relate to thought?

⚫ Mode r n linguistics and AI, then, were “born” at about the

same time, and grew up together, intersecting in a hybrid
fi eld called computational linguistics or natural language
processing.

46
 THE HISTORY OF ARTIFICIAL
INTELLIGENCE
The inception of artificial intelligence (1943-1956)

⚫ T h e fi rst work that is n o w generally recognized as AI

was done by Warren McCulloch and Walter Pitts (1943).
⚫ T h e y proposed a model of artificial neurons. Year 1949:
Donald Hebb demonstrated an updating rule for modifying the
connection strength between neurons. His rule is n o w called
Hebbian learning.
Early enthusiasm, great expectations (1952-1969)

⚫ T h e intellectual establishment of the 1950s, b y and large,

preferred to believe that “a machine can never do X”. John
McCarthy referred to this period as the “Look, Ma, no
hands!” era.
A does of reality (1966-1973)
47 ⚫ In almost all cases these early systems failed on m o r e
 THE HISTORY OF ARTIFICIAL
INTELLIGENCE
Expert systems (1969-1986)
⚫ T h e picture of problem solving that had arisen during the
fi rst decade
of AI research was of a general-purpose search mechanism
trying to string together elementary reasoning steps to fi nd
complete solutions. Such approaches have been called weak
methods. T h e alternative to weak methods is to use m o r e
powerful, domain- specifi c knowledge
that allows larger reasoning steps and can m o r e easily handle
typically occurring cases in narrow areas of expertise.
The return of neural networks (1986-present)
⚫ In the mi d- 1980s at least four diff erent groups reinvented
the back-
propagation learning algorithm fi rst developed in the early
1960s.
48
THE HISTORY OF ARTIFICIAL
INTELLIGENCE
Probabilistic reasoning and machine learning (1987-present)
⚫ In the 1980s, approaches using hidden Markov models
(HMMs) came
to dominate the area. Pearl’s development of Bayesian
networks yielded a rigorous and eff icient formalism for
representing uncertain knowledge as well as practical
algorithms for probabilistic reasoning.
Big data (2001-present)

⚫ Remarkable advances in computing power and

the creation of the Worl d Wi de We b have facilitated the
creation of ver y large data sets—a p h e n o me n o n
sometimes known as big data.
Deep learning (2011-present)
⚫ T h e term deep learning refers to m a c hine learning using
multiple layers of
1990s
 The State of the Art
● R O B O T I C VEHICLES
● LEGGED L O C O M O T I O N
● A U T O N O M O U S PLA NNI NG A N D
SCHEDULI NG
● MAC H I NE T R A N S L AT I O N
● SPEECH R E C O G N I T I O N
● R E C O M M E N D AT I O N S
● G A M E PLAYING
● IMAGE UND ERSTAND I NG
● MEDICINE
● C L I M AT E SCIENCE

50
 Applications of
AI problems that required thinking b y humans:
Solving
● Playing games (chess, checker, cards, ...)
● Great advances: the AI software De e p Blue beats
h u m a n expert Kasparov.
● Proving theorems (mathematical theorems, laws o f
physics, …)
● Classifi cation o f text (Politics, Economic, Social,
Sports, etc,)
● Information fi ltering and summarization o f text
● Writing story and poems; solving puzzles
● Giving advice in Medical diagnosis, Equipment repair,
Com puter confi guration, Financial planning,

51
 How to make computers
act like humans?
T h e following sub-fi elds have emerged
● Natural Language processing (enable computers to
communicate in human language, English, Amharic, ..)
● Knowledge representation (schemes to store information,
both facts and inferences,…)
● Automated reasoning (use stored information to answer
questions and to draw new conclusions)
● Machine learning (adapt to new circumstances and
accumulate knowledge)
● Computer vision (recognize objects based on patterns in
the same
way as the human visual system does)
● Robotics (produce mechanical device capable of controlled
motion with the ability to move, see, hear, and accordingly
52
take actions in the world, possibly responding to new
 AI vs.
HI?
T h e following sub-fi elds have emerged
● Artifi cial Intelligence (or AI) is the fi eld that explores to
develop a system that think in the same sense as
humans do.
● Re me mb e r computer based chess program (Deep Blue)
that beats human expert (Gary Kasparov). What do y o u
understand from this?
● Does AI equal h u m a n intelligence?
● Is it possible to create a computer system called mind?
● What is our concern in designing an Intelligent agent?
● Is it to replace h u m a n beings or to support and give
leverage
to th em so that the humans can engage themselves
in expert works?
53
 Can we build hardware
as complex as the
brain?
● H o w complicated is our brain?
● a neuron, or nerve cell, is the basic information processing
unit in our brain
● estimated to be o n the order o f 10 p o w 11 neurons in a
h u m a n brain
● m a n y m o r e synapses (10pow14) connecting these neurons

● cycle time: 10 p o w - 3 seconds (1 millisecond)

● H o w compl ex can we make computers?

● 106 or m o r e transistors per CPU
● supercomputer: hundreds o f CPUs, 10pow9 bits o f RAM

● cycle times: order o f 10pow- 8 seconds

● Conclusion
● POSSIBLY: in the future w e m a y have computers with as
m a n y basic
processing elements as our brain, but with far fewer
54
like a
interconnections (wires or synapses) than the brain and m u c h
 Can Computers Talk?
● This is known as “speech synthesis”
● tra nslate text to phonetic for m
●
● e.g., “fi ctitious” -> fi k-tish-es
us e pronunciation rules to m a p p honem es to actual sound
●
e.g., “tish” -> sequence of basic audio sounds

● Diff iculties
●
● sounds m a d e b y this “lookup” approach sound unnatural
so unds are not independent
●
e.g., “act” and “action”

● m o d e r n 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: N O, for complete sentences, but YES for

individual words
55
 Can Computers Recognize
Speech?
● Speech Recognition:
● mappin g sounds f r o m a microphone into a list of
words.
● Hard problem: noise, m o r e than one person
talking,
occlusion, speech variability,..
● Even if we recognize each word, we m a y not
understand its meaning.
● Recognizing single words f r o m a small
vocabulary
● systems can do this with high accuracy (order of
99%)
● c omputer tries to recognize y o u first, if unsuccessful hands y o u over to
● e.g.,aoperato
r
directory inquiries
human

56 ● limited vocabulary
saves millions (area acodes,
of dollars citythe
year for names)
phone companies
 Recognizing human speech
(ctd.)
● Recognizing normal speech is m u c h m o r e diff icult
● speech is continuous: where are the boundaries between
words?
● e.g., “John’s car has a fl at tire”

● large vocabularies
● can be m a n y tens of thousands of possible words
we can use context to help fi gure out what s omeone said
●
try telling a waiter in a restaurant:
“I would like s ome cream and sugar in m y coff ee”

● background noise, other speakers, accents, colds, etc

● on normal speech, moder n systems are only about
60% -70% accurate
● Conclusion: N O, normal speech is too c omple x to
accurately
recognize, but YES for restricted problems
57
● (e.g., recent software for P C use b y IBM, Dragon
systems, etc)
 Can Computers Understand
speech?
● Understanding is diff erent to recognition:
● “ T i m e fl ies like an arrow”
● assume the computer can recognize all the words. but
h o w could it understand the sentence
● 1. time passes quickly like an arrow?
● 2. c ommand : time the fl ies the w a y an arrow times the
fl ies
● 3. c ommand : only time those fl ies which are like an arrow

● 4. “time-fl ies” are fond o f arrows

● only 1. makes any sense, but h ow could a
this
computer fi gure
out?
● clearly humans use a lot of implicit c ommonsense knowledge in communication

● Conclusion: N O, m u c h o f what w e say is

capabilities o f a computer to understand
b e y o n at
d the
58 present
 Can Computers Learn
and Adapt ?
● Learning and Adaptation
● consider a computer learning to drive on the
freeway
● we could code lots of rules about what to do
● and/or we could have it learn f r o m experience
Darpa’s Grand Challenge. Stanford’s
“Stanley” drove 150 km without
supervision in the Majove dessert

● machine learning allows computers to learn to do

things without explicit programming

● Conclusion: YES, computers can learn and

adapt, when presented with information in the

59
appropriate way
 Can Computers
“see”?
● Recognition v. Understanding (like Speech)
● Recognition and Understanding of Objects in a
scene
● look around this r o o m
● y o u can eff ortlessly recognize objects

● h u m a n brain can m a p 2D visual image to 3D “map”

● W h y is visual recognition a hard problem?

Conclusion: mostly NO : computers can only “see”

certain
types of objects under limited circumstances: but
certain constrained problems (e.g., face
60 YES for
recognition)
 Must an Intelligent System be
Foolproof?
● A “foolproof ” system is one that never makes an
error:
● T y p e s of possible computer errors
● hardware errors, e.g., m e m o r y errors

● software errors, e.g., coding bugs

● “human- like” errors

● Clearly, hardware and software errors are possible in

practice
● what about “human-like” errors?

● An intelligent system can make errors and still be

intelligent just like humans w h o apparently are not
right all of the time
● we learn and adapt f r o m making mistakes
● e.g., consider learning to surf, ski, or ride a bike

6 ● we im prove b y taking risks and falling

1
● an intelligent system can learn in the same way
 Programming paradigms
● Each p r o g r a m m in g paradigms consists o f two
aspects:
● Methods for organizing data/knowledge,
● Methods for controlling the fl ow of computation
● Traditional paradigms:
Programs = data structure + control
● AI programmin g paradigms:
Programs = knowledge structure +
inference

62
 Risks and Benefits of
AIL E T H A L A U T O N O M O U S
●
WEAPONS
● SURVEILLANCE A N D
PERSUASION
● BIASED D E C I S I O N M A K I N G
● I M PA C T O N E M P L O Y M E N T
● SAFETY-C R I T I C A L
A PP LI C ATI O N S
● C YBE RSECU R ITY

63
The End of Topic 1