Chapter one

Artificial Intelligence
 What is Artificial intelligence?
• It is the combination of two words i.e.
• Artificial :-none natural/man made /formulate
• Intelligence:-the ability to understand, think or
learn some thing.
• Intelligence is the capability of observing,
learning, remembering and reasoning.
• Artificial intelligence is the ability of creating
the system that can be understand, think and
learn some thing from the environment
 Cont’d
 Is an area of science and engineering that
emphasizes the creation of intelligent machines
that work and react like humans.
It is related to the similar task of using
computers to understand human intelligence,
 Build and understand intelligent entities or
agents
 Cont’d
• It is a branch of computer science concerned with:

The study and creation of computer system exhibit

some form of intelligence.

System that learn new concepts and tasks

System can reason and draw conclusions

Can understand NLP

 Cont’d
• Artificial Intelligence is the synthesis and analysis of
computational agents that act intelligently.
• An agent is something that acts in an environment.

• An agent acts intelligently if:

– its actions are appropriate for its goals and circumstances
– it is flexible to changing environments and goals
– it learns from experience
– it makes appropriate choices given perceptual and
computational limitations
 Cont’d
• The concern of AI is to enable computers behave like
human and emulate the reasoning power of humans
• in order to do tasks that require human intelligence.
– Which task requires intelligence?
– Complex arithmetic operations
– For instance, Solving 220 * 350?
– Mundane tasks/routine
– Example, Natural language understanding; face recognition
– Expert tasks:
– which require specialists knowledge
– Example, Medical diagnosis; computer maintenance
 Intelligence
ocalculate, o use natural

o reason, language fluently,

o classify,
o perceive relationships and
o generalize, and
analogies,
o adapt new
o learn from experience,
situations.
o store and retrieve information
from memory,
osolve problems,
ounderstand complex ideas,
 Intelligence
• Intelligence is composed of several
component
Reasoning
Learning
Problem solving
Perception
Linguistic perception
 History of AI
• Formally initiated in 1956 and the name AI was coined by

John McCarthy.(Stanford University)

• Shifts from procedural to declarative programming paradigm.
– Rather than telling the computer how to compute a solution, a program
consists of a knowledge base of facts and relationships.
– Rather than running a program to obtain a solution, the user asks question
so that the system searches through the KB to Simulate human mind and
learning behavior to determine the answer.
– Simulate human mind and learning behavior (Neural Network, Belief
Network, Hidden Markov Models, etc. )
 History of AI…
• Development of knowledge-based systems: (1969-1979) the key to power
– Performance of general-purpose problem solving methods is weak for
many complex domains.
– Use knowledge more suited to make better reasoning in narrow areas of
expertise (like human experts do).
– Early knowledge intensive systems include:
• MYCIN (1976): used for medical diagnosis. etc.
• The Dendral program (1969): solved the problem of inferring
molecular structure (C6H13NO2).(A chemical analysis expert system)
 History of AI…
• A1 becomes an industry (1980-present)
o to build intelligent computers running Prolog.

 AI becomes a science (1987-Present)

 The emergence of intelligent agents (1995-present)

 Goals of artificial
intelligence
 To Create Expert Systems: The systems which
exhibit intelligent behavior, learn, demonstrate,
explain, and advice its users.

 To Implement Human Intelligence in

Machines: Creating systems that understand,
think, learn, and behave like humans.
 Strong AI vs. Weak AI
• Artificial Intelligence (or AI) is the concept that it is possible for a
computer to think in the same sense as humans do.
• Week AI-
- Thinking focused towards the dev’t of technology capable of caring
out pre-planned moves based on some rules and applying these to
achieve a certain goal.
o Uses models of its problem domain given to it by programmer.
o A system that uses a set of pre-programmed rules to apply them to any task to
reach a successful completion.

- argues that computers can only appear to think and are not
actually conscious in the same way as human brains are.

- For example, weak AI researchers see their contribution as things like expert
systems used for medical diagnosis, speech recognition and data mining, which
use "intelligent" models, but they do not help create a conscious agent
 Strong AI vs. Weak AI…
• Strong AI
– Developing technology that can think and
functions similar to humans, not just mimicking
behavior in a certain domain.
- Machines the ability to reason, think and do all
functionality that a human is capable of.
- Figure out its own model based on raw inputs.
– aims to create an agent that can replicate
humans intelligence completely; i.e.., it can
think, reason, imagine, etc., and do all the things
that we currently associate with the human brain.

– Have self awareness, feel emotions, dream,

consciousness, think etc.
 The foundation of AI
With different disciplines:
• Philosophy

• Mathematics

• Law

• Economics

• Computer engineering
Foundation …
 Views of AI
• AI is found on the premise that:
– workings of human mind can be explained in
terms of computation, and
– computers can do the right thing given correct
premises and reasoning rules to achieve a
specified goal.
Views of AI
Thinking fall into four
humanly categories:
Thinking rationally

Acting humanly Acting rationally

Thinking humanly: The Cognitive
Modeling
• Reasons like humans do
– Programs that behave like humans
• Requires understanding of the internal activities of the
brain
- Cognitive modeling is an area of computer
science that deals with simulating human problem
solving and mental task processes in a
computerized model.
• AI can develop automated intelligent machine which
can perform different activities which
associated with human thinking activities such
as decision making, problem solving, adapt new env’t
and learning new things.
Example. write a program that plays chess.
– Instead of making the best possible chess-playing
 Acting humanly: The Turing
Test
Can machines act like human do? Can machines behave
intelligently?
• Turing Test: Operational test for intelligent behavior
• Suggested major components required for AI:

knowledge, reasoning, language/ image

understanding, learning
How to make computers act like humans?
• Natural Language processing (enable computers
communicate in human language, English, Amharic, Oromifa..)
• Knowledge representation (schemes to store information,
both facts and inferences, before and during interrogation)
• Automated reasoning (use stored information to answer
questions and to draw new conclusions)
• Machine learning (adapt to new circumstances and to detect
& extrapolate patterns)
• Computer vision (recognize objects based on patterns in the
same way as the human visual system does)
Thinking Rationally: The Laws of
Thought
• A system is rational if it thinks/does the right
thing through correct reasoning.
• The AI system should represent facts and
concepts about the world via logic
• Aristotle: provided the correct arguments/ thought
structures that always gave correct conclusions
given correct premises.
– Aleazar is a man; all men are mortal; therefore
Aleazar is mortal
– These Laws of thought governed the operation of
 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 how the
world works
 Application of AI
 Playing Games
- AI plays crucial role in strategic games such
as chess, poker, tic-tac-toe, etc., where machine
can think of large number of possible
Eg Flight-tracking systems,
positions based on heuristic knowledge.
Clinical systems

 Expert Systems
- There are some applications which integrate
machine, software, and special information to
impart reasoning and advising. They provide
explanation and advice to the users.
 Vision Systems
- Systems that recognize objects based on
patterns in the same way as the human visual
system does.
 Natural Language Processing
Cont’d
- It is possible to interact with the computer that
understands natural language spoken by humans.
Eg. Machine Translation, text- to-speech, summarization of text,
Eg. open Eg Automatic voice output
 Speech Recognition
- Some intelligent systems are capable of hearing and
comprehending the language in terms of sentences and their
meanings while a human talks to it. It can handle different accents,
slang words, noise in the background, change in human’s noise
due to cold, etc.
 Handwriting Recognition
Software that reads the text written on paper by a pen or
on screen by a stylus. It can recognize the shapes of the letters
and convert it into editable text.
Research Areas of AI