Introduction to AI, Lecture 1, Intelligent Systems

1. Introduction
D.R.V.L.B Thambawita

2. Outline
• Course overview
• What is AI?
• A brief history
• The state of the art

3. CST 361 – 3
Intelligent Systems
• Assignments – 40%
• Main quiz – 20%
• Programming assignments 1- 10%
• Programming assignments 2- 5%
• Quiz – 5%
• End Exam – 60%
• 4 essay questions

4. Reference
• Russell, S and Norvig, P , 2009, Artificial Intelligence: A Modern
Approach , 3rd Edition, Prentice Hall, New Jersey

5. Course
overview

6. AI?

7. Intelligent Machines – Dream or reality?
AI is no longer a dream. AI techniques have shown their
potential to solve various problems including the
development of smart space robot, complex scheduling
and planning systems, auto pilot systems and
recognition of objects in complex scenes, which cannot
be achieved otherwise. In many instances, AI programs
have gone beyond human level performance, and even
defeated grand chess mater.

8. AI definitions
• A branch of computer science dealing with the simulation of intelligent
behavior in computers
• The capability of a machine to imitate intelligent human behavior
www.merriam-webster.com
• Artificial intelligence (AI) is intelligence exhibited by machines.
Wikipedia
• The study and design of intelligent agents, where an intelligent agent is
a system that perceives its environment and takes actions that
maximize its chances of success.
Russel and Norvig AI book

9. What is AI?
Thinking Humanly Thinking Rationally
Acting Humanly Acting Rationally
Views of AI fall into four categories

10. What is AI?

11. What is AI?
Thinking humanly: The cognitive modeling
approach
• Once we have a sufficiently precise theory of the mind, it becomes possible
to express the theory as a computer program
• If the program’s input–output behavior matches corresponding human
behavior, that is evidence that some of the program’s mechanisms could
also be operating in humans.
• The interdisciplinary field of cognitive science brings together computer
models from AI and experimental techniques from psychology to construct
precise and testable theories of the human mind.
• cognitive science: the study of thought, learning, and mental organization,
which draws on aspects of psychology, linguistics, philosophy, and
computer modelling.

12. What is AI?
Acting humanly: The Turing Test approach
Turing test (Alan Turing 1950): A computer passes the test of intelligence, if
it can fool a human interrogator.

13. What is AI?
Acting humanly: The Turing Test approach
• The computer would need to possess the following capabilities: (for
the Turing test)
• Natural language processing to enable it to communicate successfully in
English
• Knowledge representation to store what it knows or hears
• Automated reasoning to use the stored information to answer questions and
to draw new conclusions
• Machine learning to adapt to new circumstances and to detect and
extrapolate patterns
Turing’s test deliberately avoided direct physical interaction between the
interrogator and the computer, because physical simulation of a person is
unnecessary for intelligence

14. What is AI?
The Total Turing Test
• To pass the total Turing Test, the computer will need (additionally)
• computer vision to perceive objects, and
• robotics to manipulate objects and move about

15. What is AI?
Thinking Rationally: The “laws of thought” approach
• Formalize “correct” reasoning using a mathematical model (e.g. of
deductive reasoning).
• Logistic Program: Encode knowledge in formal logical statements and
use mathematical deduction to perform reasoning:
• Problems:
• Formalizing common sense knowledge is difficult.
• General deductive inference is computationally intractable.

16. Acting rationally: The rational agent approach
• Rational behavior: doing the right thing
• A rational agent is one that acts so as to achieve the best outcome or,
when there is uncertainty, the best expected outcome.

17. Applications of AI
• Speech recognition
• Siri (Apple),
• Echo (Amazon),
• Google Now,
• Cortana (Microsoft).
• Leverage deep neural networks to handle speech recognition and
natural language understanding

18. Applications of AI
• Handwriting recognition

19. Applications of AI
• Machine translation

20. Applications of AI
• Robotics

21. Applications of AI
• Recommendation systems

22. Applications of AI
• Search engines

23. Applications of AI
• Face detection and recognition

24. Applications of AI
Deep Blue (chess computer)

25. • Target-
• Covering all the content before the first week of April

26. Summary
• Course overview
• What is AI?
• A brief history
• The state of the art