Course Overview for Artificial Intelligence (CIS 479)

What is Artificial Intelligence?

 

Why Study Artificial Intelligence?

Heuristic Programming

How can you tell if a machine is intelligent?

Turing Test

 Can/Should Computers replace human experts?

 Good Problems For Artificial Intelligence

  1. Decomposable to easier problems
  2. Solution steps can be ignored or undone
  3. Predictable Problem Universe
  4. Good Solutions are obvious
  5. Internally consistent knowledge base (KB)
  6. Requires lots of knowledge or uses knowledge to constrain solutions
  7. Interactive

Goals for Artificial Intelligence (AI)

  1. Make computers more useful
  2. Understand Principles of Human Intelligence

Newell/Simon Physical Symbol Hypothesis

Artificial Intelligence (AI) Technique

  1. Capture generalizations
  2. Understood by domain expert
  3. Easily modified to correct errors
  4. Used in lots of different situations
  5. Reduce its own size/bulk, this does not spend the entire time looking at the whole domain

Successful Artificial Intelligence (AI) Applications

  1. Usually operate in a restricted domain
  2. Tend to exhibit goal directed planning behavior
  3. Some reasoning or explanation mechanism

Taxonomy of Artificial Intelligence System (From Easiest to Hardest)

  1. Data acquisition
  2. Expert System (Automatic Programming, Problem Solving)
  3. Robotic Control
  4. Pattern Recognition
  5. Natural Language Processing
  6. Vision & Scene Analysis

Criteria for Success