1 / 26

Artificial Intelligence Programming

Artificial Intelligence Programming. Course CS II Prof. Dr. U. Quevedo University of Wisconsin- Parkside. International Summer University 2011. University of Wisconsin-Parkside.

alima
Télécharger la présentation

Artificial Intelligence Programming

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Artificial Intelligence Programming Course CS II Prof. Dr. U. Quevedo University of Wisconsin-Parkside

  2. International Summer University 2011

  3. University of Wisconsin-Parkside UW-Parkside is one of 13 four-year campuses in the University of Wisconsin System. UW-P is located in Kenosha, Wisconsin, between Milwaukee and Chicago on 700 acres with natural prairies and woodlands.

  4. Chicago Kenosha Milwaukee

  5. Computer Science Department • The department offers a high quality Bachelor of Science in Computer Science and a Master of Science in Computer and Information Systems.

  6. Success stories • Our programs are highly respected in the region with virtually 100% of our students employed in professional positions when they graduate

  7. Course Syllabus • Course Description • Resources • Schedule • Format / Activities • Grading

  8. What is Artificial Intelligence?

  9. Artificial Intelligence • Artificial Intelligence is the study of how to make computers do things at which, at the moment, people are better. • Artificial Intelligence is the branch of computer science that is concerned with the automation of intelligent behavior.

  10. What is Intelligence?

  11. Intelligence • Intelligence is the computational part of the ability to achieve goals in the world. • Isn't there a solid definition of intelligence that doesn't depend on relating it to human intelligence?

  12. Other Basic Questions • How to identify “intelligent behavior”? • What is an intelligent computer program? • Alan Turing discussed conditions for considering a machine to be intelligent.

  13. Turing Test • Turing argued that if the machine could successfully pretend to be human to a knowledgeable observer then you certainly should consider it intelligent. • The observer could interact with the machine and a human by teletype (to avoid requiring that the machine imitate the appearance or voice of the person), and the human would try to persuade the observer that it was human and the machine would try to fool the observer

  14. The Anti-Turing test: Captcha • A CAPTCHA is a program that can generate and grade tests that humans can pass but current computer programs cannot.

  15. Principles of Computer Science needed in AI • Data Structures (knowledge representation, scheme) • Algorithms (needed to apply knowledge) • Languages (the medium of implementation) • Programming Techniques

  16. AI Languages • AI languages should be constrained to take the form of explicit structures for representing categories of knowledge. • Programming languages are the medium of implementation; the data structure is the scheme. • Their medium of implementation might be Prolog, Lisp or more common languages like C++ or Java.

  17. Knowledge representation languages • These are high level representation formalisms, and can in principle be implemented using a whole range of programming languages • They should support inference

  18. Inference Mechanism • We can't represent explicitly everything that the system might ever need to know – some things should be left implicit, to be deduced by the system as and when needed in problem solving. • Examples: • Smart people -> computer science students • X is not the president of the U.S. • Location of Y’s office

  19. A good knowledge representation language • It should allow you to express the knowledge you wish to represent in the language • It should allow new knowledge to be inferred from a basic set of facts • It should be clear, and have a well defined syntax and semantics

  20. Languages • Prolog (Swi-Prolog) • How to create, load prolog programs and execute queries • MatLab(SciLab) • How to load and manipulate images

  21. Prolog Facts: statement assumed to be true Predicates: relations that are either true or false Rules: if-then statements

  22. Family facts and relations • Facts and relations are defined in lower case, and they end with a period. male(john). female(mary). mother(mary, john). Data types like “atoms“ are indicated using lower case too.

  23. Statements and Variables • All statements end with a period. friend(John, peter). • All variables start with a capital LETTER. friend(X, peter). Prolog uses unification to solve queries.

  24. Family tree Example • Write some facts, relations and rules for: mother, father, parent, grandparent, sibling, brother, sister, married, cousins

  25. Scilab and SIVP toolbox

  26. Loading and displaying image

More Related