ISYS123

1
ISYS123

• Artificial Intelligence

2
What is Artificial Intelligence?

• AI is the study of ideas which enable computers
  to do the things that make people seem
  intelligent (Winston).
• AI is the study of how to make computers do
  things which at the moment people are better at
  (Rich)
• AI is the study of the computations that make it
  possible to reason, perceive, and act (Winston).

3
Behaviour thought to require intelligence

• ability to solve problems
• memory
• intuition
• ability to learn from experience
• ability to use tools
• ability to recognise speech
• Developing computer systems that can
• See Hear Walk Talk Feel

4
Successful AI Research

• Works in limited, well-defined domains
• Intelligent agents Daily Learner
• Autonomous vehicles
• Machine translation (parsing verbs, nouns and
  then translating words to other languages)
• Game playing like Chess
• Eliza (conversation as psychologist)

5
How do you tell if a computer is intelligent?

• Turing test (1950)
• A machine can be deemed intelligent when it can
  pass for a human being in a blind test.
• (computer, human) answer questions from
  human.depending on answers human must determine
  which answer came from a machineif fooled then
  computer deemed intelligent.
• No computer has passed test.

6
Natural Language Processing

• Speech recognition
• Language understanding
• Translation
• Language generation
• Text to speech synthesis

7
NLP Problems

• Syntax
• Semantics
• Syntactical ambiguity
• Semantic ambiguity
• Fluidity of language

8
Application - Scanning Law Reports

• Scanning the pages
• Bit map to characters (OCR)
• Characters to words
• Words to sentences
• Correctness
• Information retrieval
• Askjeeves.com

9
Example

• Askjeeves.com
• Ask itWhat is the highest point in Australia?
• One answer talks is about cricket!!

10
Expert Systems

• A software program designed to replicate the
  decision making process of a human expert.
• Examples
• Bank loans
• Credit card applications
• Medicine - diagnosis systems
• Design - Xerox paper handling systems
• Farming - CSIRO

11
What does an expert system have?

• Knowledge base a database of facts and the rules
  that determine and change the relationships
  amongst the facts.
• Human interface allows user to interact with
  system
• Inference engine puts user input together with
  knowledge base applies logical principles and
  produces requested expert advice.
• Limitations applicable to narrow specific
  domains, fields.

12
Game playing

• Chess (Deep Blue vs Kasparov)
• Search possible future moves
• Heuristics a rule of thumb (guide towards
  judgments that experience tell us to be true)
• pattern recognition patterns in moves
• machine learning learn from experience
• Robot Soccer, volleyball.

13
Computer Games

• Make use of AI
• Computer opponents in strategy games
• Computer controlled entities in first person
  shooters
• etc

14
Vision

• Hard to define in terms the computer can
  understand
• Real world objects
• move
• partially covered
• changing
• hidden by shade

15
Vision

• Enormous computer requirements
• Applications
• Zip code reader
• Security systems
• Robots

16
Robots and Neural Networks

• A Robot is a computer-controlled machine
  programmed to perform specific manual tasks
• Industrial robots, Humanoid robots, Joints.
• Neural Networks
• Computers working in parallel
• Simulating the human brain