1 / 14

IAI Final Lecture

IAI Final Lecture. Examples of AI. Spam filtering in Gmail Page ranking by Google. Number plate recognition systems Face recognition (in cameras) Handwriting recognition (personal digital assistants) Speech recognition (phone answering system). Eliza.

filia
Télécharger la présentation

IAI Final Lecture

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. IAI Final Lecture

  2. Examples of AI • Spam filtering in Gmail • Page ranking by Google. • Number plate recognition systems • Face recognition (in cameras) • Handwriting recognition (personal digital assistants) • Speech recognition (phone answering system)

  3. Eliza • Example of natural language processing. • ELIZA was named after Eliza Doolittle, a working-class character in George Bernard Shaw's play Pygmalion, who is taught to speak with an upper-classaccent. • ELIZA was written at MIT by Joseph Weizenbaum. • http://chayden.net/eliza/Eliza.html • A chat-bot written in Java. • Competitions in USA • People have given their credit card details to CYBERLOVER.

  4. Mind/Body • Is the brain/mind • The same as • Hardware/software?

  5. Free will • I have free will… • Do you have free will? • Can you define free will. • Physicists thought the universe was deterministic (billiard ball model of universe). • Humans are CHOPS+N (Nitrogen, Carbon, Hydrogen, Oxygen, Phosphorus, and Sulfur (the six elements in organic materials) • Computers are Silicon, Plastic and metal. • Why do we have free will but computers don’t? • Is free will necessary for intelligence?

  6. 1+1 • We all know 1+1 = 2 (I hope) • Do you know why? • We know -1*1 = 1 and -1*-1 =1 and 1*1 = 1 • Do you know why

  7. Darren Brown plays chess • Popular UK TV show Magician/Hypnotist. • He plays against 12 world class chess players in parallel and claims he cannot lose (i.e. he can win or draw). • How can he do this?

  8. Compression of data • Lossless compression means you can compress data and retrieve its original. • Lossy compression, means we lose some precision e.g. in images or music files. • Why is compression important in AI • What is the next number in the sequence • 1 2 3 4 5 6 7 • Can we compress all data? • Patterns are important.

  9. Halting 1 • INPUT: A string P and a string I. We will think of P as a program. • OUTPUT: 1, if P halts on I, and 0 if P goes into an infinite loop on I. • Theorem (Turing circa 1940): There is no program to solve the Halting Problem. • Proof: Assume to reach a contradiction that there exists a program Halt(P, I) that solves the halting problem, Halt(P, I) returns True if and only P halts on I. The given this program for the Halting Problem, we could construct the following string/code Z:

  10. Halting 2 Consider the following program Z Program (String x) If Halt(x, x) then Loop Forever Else Halt. End.

  11. Halting 3 • Consider what happens when the program Z is run with input Z • Case 1: Program Z halts on input Z. Hence, by the correctness of the Halt program, Halt returns true on input Z, Z. Hence, program Z loops forever on input Z. Contradiction. • Case 2: Program Z loops forever on input Z. Hence, by the correctness of the Halt program, Halt returns false on input Z, Z. Hence, program Z halts on input Z. Contradiction.

  12. Halting 4 • There are many properties of programs we cannot check e.g. is this program a virus • So how do virus checkers work? • Is there a solution to Fermat’s last theorem? • Goldbach conjecture. Every even number can be expressed as the sum of two primes.

  13. Where does understanding reside? • A robot appears intelligent. • But the robot is controlled remotely by a computer. • But the computer was programmed by a computer science student. • In what part of the students brain is intelligence stored?

  14. Can robots/computers/agents…? • Become depressed? • Fall in love and have emotions? • Have morals and feel emotions? • Deceive us and cheat, tell white lies? • Replace us? • Be held responsible?

More Related