Transcript Document

COMP-6600: Artificial Intelligence (Overview)
• A tentative overview of the course is as
follows:
1. Introduction to Artificial Intelligence
2. Evolutionary Computation
3. Machine Learning
Overview (cont.)
• This course will consist of:
– homework assignments (25%)
– a final exam (25%)
– a final project (50%)
• a final project presentation (10%)
[Must have a topic by week 5]
• a final project report (40%)
Brief Introduction to Artificial Intelligence
• One of the first questions we must ask ourselves concerning AI is,
“What does it mean to be intelligent?’’
• According to Webster’s New World Pocket Dictionary (3rd Edition),
Intelligence is defined as, “The ability to learn, or solve problems”.
• Fogel in (Fogel, D. B., Evolutionary Computation: Toward a New Philosophy of
Machine Intelligence, IEEE Press, 2000) defines Intelligence, “as the
capability of a system to adapt its behavior to meet its goal in a range
of environments.”
• According to our textbook there are 4 camps based on thinking/acting
humanly/rationally.
–
–
–
–
Thinking Humanly: Cognitive Modeling
Thinking Rationally: Logic
Acting Humanly: Turing Test
Acting Rationally: Intelligent Agents
Brief Introduction to Artificial Intelligence
(cont.)
• In my opinion, Intelligence is the ability to create unique
artifacts (ideas, or concepts) that previously did not exist.
– Genesis 2:19,20 NIV
– Jeremiah 32:35 NIV
• Is it possible to reliably classify an entity as intelligent by
merely observing or interacting with it?
–
–
–
–
Sphex Wasp (Fogel, 2000,p. 13; Russell & Norvig, 2003, p. 37)
Dung Beetle (Russell & Norvig, 2003, p. 37)
Eliza (Weizenbaum)
Parry
COMP-4640: Symbolic AI
• Based on Newell & Simons Physical Symbol System Hypothesis
• Uses logical operations that are applied to declarative knowledge
bases (FOPL)
• Commonly referred to as “Classical AI”
• Represents knowledge about a problem as a set of declarative
sentences in FOPL
• Then logical reasoning methods are used to deduce consequences
• Another name for this type of approach is called “the knowledgebased” approach
• The Symbol Processing Approach uses “top-down” design of
intelligent behavior.
COMP-6600: Sub-symbolic Approach
• Based on the Physical Grounding Hypothesis
• “bottom-up” style
• Starting at the lowest layers and working upward.
• In the sub-symbolic approach signals are generally used rather than
symbols
• Proponents believe that the development of machine intelligence
must follow many of the same evolutionary steps.
• Sub-symbolic approaches rely primarily on interaction between
machine and environment. This interaction produces and emergent
behavior (evolutionary robotics, Nordin, Lund)
• Some other sub-symbolic approaches are: Evolutionary
Computation, Artificial Immune Systems, and Neural Networks