Artificial Intelligence

Approaches

Lecture 1: Introduction to AI

Dr. Sheheen Abdullah Abdulkareem

About Me..
ØPhD in Computer Science – Artificial Intelligence from
University of Twente (The Netherlands) and University of
Duhok (Kurdistan-region, Iraq) in April 2019.

ØMSc in Geoinformatics from University of Twente, The

Netherlands (March 2010).

ØBSc in Computer Science from University of Duhok (UoD),

Kurdistan-region of Iraq (July 2005).

2
 Semester’s Objectives
Ø To develop an understanding of the basic concepts of AI.

ØTo explore use cases and applications of AI.

ØTo interact with people working in the field

ØTo get excited about AI!

Intelligence Definitions
ØIntelligence is the computational part of the ability to achieve
goals in the world.
oDifferent kinds and degrees of intelligence occur in people, many
animals and some machines!
ØIt is a property that an individual has as s/he interacts with
her/his environment(s).

ØIt is related to the Individual’s ability to succeed or profit with

respect to some goal or objective.

4
 Artificial Intelligence (AI)

Artificial Intelligence (AI)

ØArtificial Intelligence (AI) is a branch of Science which deals
with helping machines find solutions to complex problems in a
more human-like fashion.
oJohn McCarthy, who coined the term “Artificial Intelligence” in 1956,
defines it as “ the science and engineering of making intelligent
machines”, especially intelligent computer programs!

o“the automation of activities that we associate with human thinking

activities such as decision-making, problem solving, learning,
...”(Bellman, 1978).

6
 Goals of AI
ØThe definition of AI gives four possible goals to pursue four
approaches:
1. Systems that think like humans
2. Systems that act like humans
3. Systems that think rationally
4. Systems that act rationally

7 ØMost of AI work falls into category (3) and (4)

7

(1) Think Human-like: Cognitive Science

ØAn exciting new effort to make computers think;

ØFocus is at creating machines with minds in the full and literal

sense.
oComputational model as to how results were obtained.

ØGoal is to produce a sequence of steps of the reasoning

process, similar to the steps followed by a human in solving the

8
same task.

8
 (2) Act Human-Like: Turing Test
ØIt is the study of how to make computers do things
which at the moment people do better.

ØFocus is on actions that are pretended the computer is

human.

ØGoal is to develop systems that are human-like

behavior.
9

(3) Think Rationally: Laws of Thought

ØIt is the study of creating intelligent agent that is able to perceive,
reason, and act.

ØFocus is on inference mechanisms that are provably correct and

guarantee an optimal solution.
o Develop systems of representation to allow inference to be like “Parrot is a bird.
All birds are animals. Therefore parrot is animal”

ØGoal is to formalize the reasoning process as a system of logical rules

10
and procedures for inference.
10
 (4) Act Rationally: Rational Agent
ØTries to explain and emulate intelligent behavior in terms of
computational processes;
ØFocus is on systems that act sufficiently if not optimally in all
situations;
oIt is possible to have imperfect reasoning if the job gets done.

ØGoal is to develop systems that are rational and sufficient.

ØA system is rational if it does the right thing
11

11

AI is the study of:

ØThe design of intelligent agents, where an intelligent agent is a
system that perceive its environment and takes actions that
maximize its chances of success.

ØAI seeks to understand the computations required from

intelligent behaviour and to produce computer systems that
exhibit intelligence.

12
 Intelligent Agents

Proactive
Learn

Reactive

Making Decision

Sociable

Achieving Goals

Strategies
13

13

Human Brain
ØHow do we think?
ØHuman brain:
oConsists of 20 billion neurons
o240 trillion synapses
oNeuron size = 15 micrometer
oSynapses size = 1 micrometer
ØThree key steps:
1. The stimulus must be translated into an internal representation;
2. The representation is manipulated by cognitive processes to derive
new internal representations; and
3. These in turn are translated into action
14

14
 Representation
ØInformation needs to be in some form of representation.
oRepresenting the problem space to allow efficient search for best
solution(s).
oThe representation sometimes is the output (pattern recognition).

15

15

Thinking
ØOnce you have the
representation, you need to use
it to achieve the goal è
Rational behavior
ØRational behavior: choose
actions that maximize goal
achievement given available
information.

16

16
 Reasoning
ØReasoning can be thought of as constructing an accurate world
model è what can be logically inferred give available
information.

17

17

Learning
ØWhat if your world is
changing, how do we
maintain an accurate
model?
oLearning: adapt internal
representation so that it is as
accurate as possible.

18

18
 Problems of AI
ØThe following questions we need to think about before
we implement AI:
1. What are the underlying assumptions about intelligence?
2. How knowledge is acquired, represented, and stored?
3. What kinds of techniques will be useful for solving AI
problems?
4. At what level human intelligence can be modelled?
5. When will it be realized when an intelligent program has
been built?
19

19

Grading the Semester!

Ø100 is divided into 40% + 60 %

ØThe 60% is the grade of the Final Exam Dec 2022

ØThe 40% is for the semester activities

o20/40 is the average grade of midterm exam

o10/40 is for the practice assignments

o5/40 is for Moodle assignments

o5/40 is for quizzes!!

20
 References
Ø“Artificial Intelligence: A Modern Approach” , third edition by Stuart
Russell and Peter Norvig
Ø“Artificial Intelligence: Foundations of Computational
Agents”, Cambridge University Press, 2010
Ø“Artificial Intelligence: A New Synthesis” first edition or later by Nils
J. Nilsson
Ø“Artificial Intelligence: A system approach” by M. Tim Jones
ØDon’t forget to GOOGLE whatever you need!

21

22