Lecture #10 (10 November 2001)

Artificial Intelligence ("AI")


Overall Reading
Brookshear: Ch. 10.1-10.3, 10.6-10.7
Decker/Hirshfield: Mod. 9

Outline:

  • Preface (Ch. 10.1 [Br]; Mod. 9.1 [DH])
  • Definitions of Artificial Intelligence (Ch. 10.1 [Br]; Mod. 9.2 [DH])
  • Academics
  • Hollywood
  • Human Intelligence (Mod. 9.3 [DH]; optionally Ch. 10.4 [Br])
  • Applications (Ch. 10.6 [Br]; Mod. 9.4 [DH])
  • Natural Language (pp. 473-475 [Br]; pp. 305-309 [DH])
  • Comprehension
  • Translation
  • Generating new content
  • Recognition of Patterns (pp. 10.2 [Br]; pp. 309-309, 315-318 [DH])
  • Speech Recognition ("You talk, it types")
  • Visual Processing
  • Optical Character Recognition (OCR)
  • Image Processing
  • Reasoning and Logic (pp. 10.3 [Br]; pp. 310-315 [DH])
  • With Complete Information
  • With Incomplete Information
  • Expert Systems
  • Machine Learning (pp. 318-320 [DH]; optionally Ch. 10.5 [Br])
  • Consequences (Ch. 10.7 [Br]; Mod. 9.5 [DH])

  • Preface

    In the coming two weeks, we will examine questions of the following type:
  • Name some tasks that might be difficult for computers to accomplish?





  • Are there tasks which humans do better than computers?





  • Name a job, performed by a human, which you think could never be filled by a machine.





  • Are there computational tasks which neither computers nor humans can accomplish?






  • Definitions of Artificial Intelligence (Ch. 10.1 [Br]; Mod. 9.2 [DH])

  • Academia
    In general, the concept of computers and intelligence was brought to the forefront by Alan Turing in a 1950 paper entitled "Computing Machinery and Intelligence."

    Further work came out of a 1956 workshop at Dartmouth College sponsored by John McCarthy. In the proposal for this workshop, McCarthy used the phrase a "study of artificial intelligence."

    Three views of research within AI:

  • Weak AI: machines can be programmed to exhibit intelligent behavior.

  • Marvin Minsky: AI is "the science of making machines do things that would require intelligence if done by man."

  • The Turing Test: You are having a conversation in a 'chat room' on the web. Can you be sure whether the responses you see are coming from a human or a computer?

    If computers are ever so good at participating in coversations that you can not distinguish, then Turing says that the computer has displayed intelligence

  • Strong AI: machines can be programmed to possess intelligence and consciousness.

    Curiously, if someone claims to have a machine which possesses intelligence and consciousness, how can they prove it? How can you disprove the claim?

    We credit other humans with intelligence and consciousness, not because we are sure that they have thoughts and emotions, but because they behave as if they do.

  • Computational models of human intelligence
  • Patrick Hayes: AI is "the study of intelligence as computation."
  • Can we produce a legitimate model of the workings of the human brain? We seem to know that the brain is made up of many neurons which are interconnected. Each individual neuron has a reasonably simple behavior. It is the complex combination of them all that we don't understand.

    A comparison:

  • Brains have roughly 50 trillion bits of memory
    roughly 100 billion neurons
    with each neuron connected to roughly 1000 other neurons
    chemicals called neurotransmitters travel at the rate of perhaps 1000 feet per second.

  • Massively parallel computers have roughly similar amount of memory
    electrons travel essentially at speed of light
    but processors connected perhaps to 100 other processors.
  • Tessler: AI is "whatever hasn't been done yet."
  • Patrick Hayes: AI is "the study of intelligence as computation."

    That is, can we figure out how the human brain works. At basic level, individual neurons are rather simple.

  • Hollywood interpretations?
  • 2001: A space Oddysey ("You don't mind talking about this, do you Dave?")
  • War Games ("Shall we play a game?")
  • Short Circuit ("Number five is alive!")
  • Terminator
  • Artificial Intelligence

  • Human Intelligence (Mod. 9.3 [DH]; optionally Ch. 10.4 [Br])

    Why do we consider humans to be intelligent?

    What exactly do we do to earn that label?
    What are your views of mammals? birds? insects? amoebae? plants?
    What about machines?

  • Thinking Effortlessly: (language, vision)
    Do you consciously think about how to interpret each word and sentence of a conversation or do you just hear it?

    When you look out a window and see a tree, did you reason to figure out you are seeing a tree, or do you just know it?

  • Thinking Deeply: (analogies, metaphors)
    We can quickly relate situations to previous knowledge and experiences.

    "Thinking about this topic is like pulling teeth"

  • Thinking Hard: (conscious train of thought)

    "Three wolves and three chickens have to cross a river using a boat which can only hold two animals at a time..."

  • Creativity

  • Applications (Ch. 10.6 [Br]; Mod. 9.4 [DH])

  • Natural Language (pp. 473-475 [Br]; pp. 305-309 [DH])

    We will look at three distinct levels of ability:

  • Understanding language
  • Translating languages
  • Generating new content
  • Let's walk through the issues for each individual ability.

  • Understanding language

    What are the minimum requirements for understanding language?
    Must understand vocabulary.
    Must understand grammer (syntax)

    But we use knowledge far beyond that. There are many potential ambiguities in natural languages, due to:

  • Syntactic ambiguity

    Examples:

  • "John met Bill before he went to the store."

    Who was the person who later went to the store?

  • "They are racing horses."

    Is the word 'racing' a verb or an adjective? Is the sentance describing what kind of horses they are, or is it telling what some people are doing?

  • Semantic ambiguity

    Even if you know the part of speech, certain words have several meanings. Which one is reasonable interpretation?

    Examples:

  • "Ron lies asleep in his bed."

    'lies' is a verb. But does it mean to recline or to deceive?

    Well, it seems unlikely that someone can tell a fib while sleeping, so I probably assume that this meant Ron was reclined.

  • The need for contextual information

    Examples:

  • "The clams are ready to eat."

    Do you interpret this differently if you hear it in a restaurant versus in an aquarium?

  • "Do you know what time it is?"

    Does this have a different meaning if said by a stranger on the street than from your boss, after you walk into a meeting 20 minutes late?

  • "The bat slipped from his hand."

    Whose hand? Are we talking about a baseball player or a zoo keeper?

  • "Cinderella had a ball."

    Did she have a round object, a good time, or a formal dance? Perhaps reading more of the story would help us in understanding.

  • The need for rules of conversation

    Examples:

  • "Do you know what time it is?"

    Let's assume we already know that this is asked by a stranger on the street. Do you think the stranger is expecting you to answer, "Yes, I do."

  • "Do you know that your tire is flat?"

    Almost certainly not. This is not really a question. It is informative.

  • "I'd like to ask everyone to hold a hand up for two seconds."

    Was I simply expression my feelings or was there a question/request in this sentance?

  • The need for real-world, topical knowledge

    Examples:

  • "Norman Rockwell painted people.

    Fortunately, I happen to know that he placed his paint on canvas (as opposed to skin).

  • "Sally was fed up. She got up angrily from ther table at the restaurant and left just enough to cover the check. The waitress sneered at her as she walked out."

    So why was the waitress upset? Because it is customary to leave a tip in addition to paying the check. Of course we need to have knowledge about this real-world custom to be able to understand. No part of the text is going to make this explicit.

  • Translating languages
    To really do this well, you need to have good comprehension of first language, and then also know how to express the content in the second language.

    Certainly cannot just translate words:
    "The spirit is willing, but the flesh is weak."
    [translated to Russiona equivalent of]
    "The vodka is acceptable, but the meat has spoiled."

  • Generating new content
  • poetry (Lab 9.2 [DH])
  • imitate Shakespeare
  • psychoanalyst (ELIZA) (DeeDee)

  • Recognition of Patterns (pp. 10.2 [Br]; pp. 309-309, 315-318 [DH])
  • Speech Recognition

    Besides the issue of interpretting text, you need to convert the sound to the words. But how do you know where one word ends and the next starts? How do you determine the words, which are not always spoken in the identical way?

    People use clues such as inflections, context, expectations.

  • Visual Processing
  • Optical Character Recognition (OCR)
  • Image Processing

  • Reasoning and Logic (pp. 10.3 [Br]; pp. 310-315 [DH]) An example: the eight-puzzle.

  • With Complete Information
    production systems

  • With Incomplete Information

  • Expert Systems

    How do you keep track of huge amounts of knowledge and then use it to draw inferences. Keep track of facts; draw inferences.
    (The Decker/Hirschfield InferenceEngine)

    Keep in mind that human intelligence is tough to beat. (Example from Monty Python)
    Here is the HolyGrail logic, as a datafile which you should save to disk, and then load from within the InferenceEngine.


  • Machine Learning (pp. 318-320 [DH]; optionally Ch. 10.5 [Br])

    Repeated experiements with feedback (both positive and negative).

    Adjust parameters.

    Example: Robot throwing darts.


  • Consequences (Ch. 10.7 [Br]; Mod. 9.5 [DH])


    comp150 Class Page
    mhg@cs.luc.edu
    Last modified: 12 November 2001