Scribd
Upload
50 views14 pages

Prof. Madya Dr. Md. Nasir Sulaiman Jabatan Sains Komputer 43400 UPM, Serdang

The document introduces the basics of artificial intelligence (AI). It aims to describe typical AI tasks, outline techniques to solve AI problems, and discuss AI applications areas. Key points covered include defining AI as the automation of intelligent behavior through computer programs that perceive, reason, learn and act. Common AI techniques involve knowledge representation, searching, planning and learning. Example application areas discussed are game playing, expert systems, natural language processing, speech recognition, robotics, computer vision, machine learning and intelligent agents.

Uploaded by

Manoj Ravi Shankar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
50 views14 pages

Prof. Madya Dr. Md. Nasir Sulaiman Jabatan Sains Komputer 43400 UPM, Serdang

The document introduces the basics of artificial intelligence (AI). It aims to describe typical AI tasks, outline techniques to solve AI problems, and discuss AI applications areas. Key points covered include defining AI as the automation of intelligent behavior through computer programs that perceive, reason, learn and act. Common AI techniques involve knowledge representation, searching, planning and learning. Example application areas discussed are game playing, expert systems, natural language processing, speech recognition, robotics, computer vision, machine learning and intelligent agents.

Uploaded by

Manoj Ravi Shankar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 14

Prof. Madya Dr. Md.

Nasir Sulaiman
Jabatan Sains Komputer
43400 UPM, Serdang
Aims
•To introduce the basics of AI

Objective
You should be able :

•Describe typical AI tasks.


•Outlined the techniques required to solve AI problems.
•Discuss the AI applications area.

Prof. Madya Dr. Md. Nasir Sulaiman


Jabatan Sains Komputer
43400 UPM, Serdang
Definition

• As the branch of CS that is concerned with the


automation of intelligent behavior.

• The design and study of computer programs that


behave intelligently.

• The design and study of computer programs that


make it possible to perceive, reason and act.

Other intelligent behaviors – learning, thinking,


communicating, creativity, curiosity.
  Prof. Madya Dr. Md. Nasir Sulaiman
Jabatan Sains Komputer
43400 UPM, Serdang
AI computer programs
 Go beyond numerical computation and manipulations.
 Focus on reasoning tasks requiring intelligence.

Examples
• Chess program
• Schedule airlines and control factories.
• Control nuclear power plants.
• Diagnose problems in complicated electronic devices.
• Perform more mundane tasks like cleaning floors and
delivering mail without terrorizing your cat and
destroying your furniture.
Characteristics of Intelligent programs:

 Respond flexibly in situations that not anticipated by


the programmer.
 Can give answer from incomplete input/ fuzzy input.
 Optimal solution – not exact solution but approximate.
 Planning.
 Ability to learn from experience, training or adaptation.
 Generalize or prediction
 
We measure intelligence by observing how people solve
problems and respond in novel situation.

Prof. Madya Dr. Md. Nasir Sulaiman


Jabatan Sains Komputer
43400 UPM, Serdang
AI and Other fields
• Differ from most of psychology because of emphasis on
computation, and differ from most of CS because of
emphasis on perception, reasoning and action.

• Can be viewed as part engineering and part science.


Engineering goal – to solve real-world problems.
Scientific goal – to determine theories and practices.
Understanding the nature of human intelligence.
What AI can do ?
• to solve difficult analysis, i.e., mathematical analysis.

• to design new devices, i.e., circuit design – low cost –


to reduce the no. of components.

• to provide advice, i.e., diagnose diseases.

• to do generalization and prediction.

• to search for optimum solution.

Prof. Madya Dr. Md. Nasir Sulaiman


Jabatan Sains Komputer
43400 UPM, Serdang
Typical of AI Problems
Consider how human able to do to act intelligently in the
world, i.e., simple task, going shopping:

• Need to plan what to buy, how to get into town


and where to go.
• Navigate without bumping.
• Interpret what we see.
• Communicate effectively with people we meet
 

Prof. Madya Dr. Md. Nasir Sulaiman


Jabatan Sains Komputer
43400 UPM, Serdang
These task correspond to the following AI problems area:
• Planning:
The ability to decide on a good sequence of action.

• Vision: The ability to make sense what we see.

• Robotics: The ability to move and overcome obstacles.

• Natural language: The ability to communicate naturally.

Some tasks require specialized skills and training (expert


tasks), i.e., Medical diagnosis, Equipment repair,
Financial planning
AI Techniques
The most fundamental concern of AI researchers :
• Knowledge representation - to represent knowledge in a
formal manner.

• Searching - explores a space of problem states, i.e.,


successive/alternative moves, i.e., game playing step or a
doctor considers an alternative diagnoses.

• Planning

• learning

Prof. Madya Dr. Md. Nasir Sulaiman


Jabatan Sains Komputer
43400 UPM, Serdang
Overview of AI Applications/ Advanced Topics

Game playing
 

• To develop intelligent programs that can play games such as


chess.
Expert systems/ Knowledge-based systems
• Computerized advisory and/or decision-making systems that
attempt to imitate the reasoning processes and knowledge
experts in solving domain-specific problems.
• Domain expert (i.e., doctor) + Knowledge engineer (AI expert).

Natural language processing


• Natural language technology attempts to give computer users
the ability to communicate with computer in natural
language.
• Also deal with an understanding textual language for various
applications.
 

Prof. Madya Dr. Md. Nasir Sulaiman


Jabatan Sains Komputer
43400 UPM, Serdang
Speech recognition
• The recognition of the spoken language by a computer.
• Breaking up of speech into meaningful units, i.e., words.

Robotics and sensory systems


• Combining robots having mechanical motions with sensory systems
to produce machines of varying intelligence and abilities.
• A robot sense its environment and modifies its behavior on the basis
of the information gained.
 
Computer vision
• To understand digitized visual information received from a sensor
and then making a decision – interpreting a visual scene

Prof. Madya Dr. Md. Nasir Sulaiman


Jabatan Sains Komputer
43400 UPM, Serdang
Machine learning
• The ability to learn is one of the most important component of
intelligent behavior.
• Learning via symbolic-based, neural networks or
evolutionary/genetic.
• Neural networks –to mimic the neural structure of the human brain.
 
Intelligent Computer-Aided Instructions
• To develop machine that can tutor humans in an interactive
manner, such as teaching problem skills, simulations, discovery &
learning, drill and practice, etc.
 
Intelligent Databases – Data mining
• Intelligently managing large databases through complex queries and
automatically gleaning hidden information from data bases.

Intelligent Agents/ Software Agents


• Autonomous system
Example systems
• Language translations systems
• Speech to text system (or vice versa)
• Air traffic control system
• Automated personal system
• Supervisory systems
• Intelligent highways – traffic monitoring
• Robot for hazardous conditions
• Expert systems for law, medicine, counseling, etc.
• Neural network simulation on finance, stocks, medicine,
• Executive summary producing systems.
• Automatic programming
• Intelligent design in architecture, mechanical and electrical systems.
• Chess playing systems
• Medical diagnostic systems

You might also like