CH-1 Introduction To AI

Download as ppt, pdf, or txt
Download as ppt, pdf, or txt
You are on page 1of 28

Chapter One

Introduction to
Artificial Intelligence

Compiled by Wasyihun S(MSc.) 1


Learning objectives: at the end of
the class, you should be able to:
– Describe what is Artificial intelligence?

– Assess the History of Artificial intelligence

– Identify the goals of Artificial intelligence

– To know application area of Artificial intelligence

– To know the research area of AI

Compiled byWasyihun S(MSc.) 2


What is Artificial intelligence?
 Is an area of science and engineering that
emphasizes the creation of intelligent machines
that work and react like humans.
o It is related to the similar task of using
computers to understand human intelligence,

 Build and understand intelligent entities or


agents

Compiled byWasyihun S(MSc.) 3


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


Compiled byWasyihun S(MSc.) 4
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 Compiled byWasyihun S(MSc.) 5
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

Compiled byWasyihun S(MSc.) 6


– Describe what is Artificial intelligence?

– Assess the History of Artificial intelligence

– Identify the goals of Artificial intelligence

– To know application area of Artificial

intelligence

– To know the research area of AI


Compiled byWasyihun S(MSc.) 7
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,
Compiled etc. )S(MSc.)
byWasyihun 8
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)
Compiled byWasyihun S(MSc.) 9
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)

Compiled byWasyihun S(MSc.) 10


– Describe what is Artificial intelligence?

– Assess the History of Artificial intelligence

– Identify the goals of Artificial intelligence

– To know application area of Artificial

intelligence

– To know the research area of AI


Compiled byWasyihun S(MSc.) 11
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.

Compiled byWasyihun S(MSc.) 12


The foundation of AI
With different disciplines:
• Philosophy

• Mathematics

• Law

• Economics

• Computer engineering
Compiled byWasyihun S(MSc.) 13
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 fall into four categories:
Thinking humanly Thinking rationally

Acting humanly Acting rationally

Compiled byWasyihun S(MSc.) 14


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 program, you
would make one that play chess like people do.
Compiled byWasyihun S(MSc.) 15
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)
• Robotics (produce mechanical device capable
Compiled of controlled
byWasyihun S(MSc.)motion; which enable computers
16 to
see, hear & take actions)
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 the mind and initiated
the field of Logic.
Compiled byWasyihun S(MSc.) 17
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
Compiled byWasyihun S(MSc.) 18
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

Compiled byWasyihun S(MSc.) 19


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. Compiled byWasyihun S(MSc.) 20
– Describe what is Artificial intelligence?

– Assess the History of Artificial intelligence

– Identify the goals of Artificial intelligence

– To know application area of Artificial

intelligence

– To know the research area of AI


Compiled byWasyihun S(MSc.) 21
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 positions based on heuristic knowledge.
Eg Flight-tracking systems, Clinical
 Expert Systems 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.

Compiled byWasyihun S(MSc.) 22


Cont’d
 Natural Language Processing
- 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 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
Compiled byWasyihun S(MSc.) 23
and convert it into editable text.
Cont’d
 Classification of text (Politics, Economic, Social,
Sports, etc,)

 Automated fraud detection

 Automated face recognition

 Signature Recognition
Industrial robots for moving, spraying,
painting, precision checking, drilling, cleaning,
coating, carving etc.

• Intelligent Robots
- produce mechanical device capable of controlled
motion; which enable computers to see, hear & take actions
- In addition, they Compiled
are capable of S(MSc.)
byWasyihun learning from their mistakes
24
and they can adapt to the new environment.
– Describe what is Artificial intelligence?

– Assess the History of Artificial intelligence

– Identify the goals of Artificial intelligence

– To know application area of Artificial

intelligence

– To know the research area of AI


Compiled byWasyihun S(MSc.) 25
Research Areas of AI

Compiled byWasyihun S(MSc.) 26


Assignment I (due: 10 days)
• Discuss one of the following concepts. Refer at least five
sources (books, articles). present in class and send via
email.
• Application areas (answer questions like what; how;
challenges; application)
– Natural Language Processing [1]
– Natural Language Generation [2]
– Speech Recognition; Speech synthesis ; Speaker Identification [3]
– Optical Character Recognition (OCR),Writer identification [7]
– Face recognition; script recognition [4]
– Knowledge discovery in databases [5]
– Computer vision and robotics[6]

Compiled byWasyihun S(MSc.) 27


አመሰግናለሁ !!!

Compiled byWasyihun S(MSc.) 28

You might also like