This document provides an overview of artificial intelligence. It defines intelligence as the ability to plan, solve problems, reason, learn, understand new situations, and apply knowledge. AI is described as building intelligent systems that can think and act like humans or rationally. The history of AI is discussed, from its origins in the 1950s to current applications. Key concepts to be learned in the semester include problem solving, machine learning, evolutionary computation, robotics, and intelligent agents. Python and NetLogo will be used as tools.
2. What is Intelligence?
• Simply, it defined as set of properties of the mind!
• The properties include the ability to plan, solve problems, and
reason.
• Simpler, is the ability to make right decision given a
set of inputs and variety of possible action
• The ability to learn or understand or to deal with new or trying
situations!
• The ability to apply knowledge to manipulate one's environment
or to think abstractly as measured by objective criteria (as
tests)!
3. What is AI?
• Not just making Computers, Robots, or agents
acts like humans!
– They should think like humans not like machines!
– We don’t want them to make humans mistakes!
– We want them to learn but not from the time 0!
• The key is the ability to “share” learned results
(i.e. copy data/program) between computers.
5. So…
• AI is not just studying intelligent systems, but
building them…
• Psychological approach: an intelligent system is
a model of human intelligence!
• Engineering approach: an intelligent system
solves a sufficiently difficult problem in a
generalizable way!
6. The AI Semester Objectives
• Become familiar with AI techniques, including
their implementations
– be able to develop AI applications using Python!
• Understand the theory behind the techniques,
knowing which techniques to apply when (and
why)
• Become familiar with a range of applications of
AI
– We will focus on Agent-based Modelling and
applying it using NetLogo software!
7. AI History?
• Gestation (the early 1950’s):
– McCulloch and Pitts artificial neuron, Hebbian
learning
– Early learning theory, first neural network, Turing test
• Birth (1957):
– The Logic Theorist
– Name coined by McCarthy
– Workshop at Dartmouth
8. Cont’d…
• Early enthusiasm, great expectations (1952-
1969)
– GPS, physical symbol system hypothesis
– Geometry Theorem Prover (Gelertner), Checkers
(Samuels)
– Lisp (McCarthy), Theorem Proving (McCarthy),
Microworlds (Minsky et. al.)
– “neat” (McCarthy @ Stanford) vs. “scruffy” (Minsky
@ MIT)
9. Cont’d…
• Dose of Reality (1966-1973)
– Combinatorial explosion
• Knowledge-based systems (1969-1979)
• AI Becomes an Industry (1980-present)
– Boom period 1980-88, then AI Winter
• Return of Neural Networks (1986-present)
• AI Becomes a Science (1987-present)
– SOAR, Internet as a domain
10. What is AI (Again)?
• Systems that think like • Systems that think
humans! rationally!
• Cognitive Modeling Approach – Laws of Thought approach
• The automation of activities – The study of mental faculties
that we associate with human through the use of computational
thinking... models.
• Systems that act like • Systems that act rationally!
humans! • Rational Agent Approach
• Turing Test Approach • The branch of CS that is
• The art of creating machines concerned with the automation of
that perform functions that intelligent behavior
require intelligence when
performed by people
11. Acting Humanly!
• Turning Machine: Introducing the concept of his
universal abstract machine.
– Simple and could solve any mathematical problem.
• Turning test: if the machine could fool a human into
thinking that it was also human, then it passed the
intelligence test.
Can Machines Think?
12. Acting Humanly, Cont’d…
• Operational test for intelligent behavior
• The Imitation Game
• Problem!
– The turning test is not reproducible, constructive, or
amenable to mathematical analysis
13. Thinking Humanly!
• 1960’s cognitive revolution
• Requires scientific theories of internal activities
of the brain
• What level of abstraction? “Knowledge” or “Circuits”
• How to validate?
– Predicting and testing behavior of human subjects (top-down)
– Direct identification from neurological data (bottom-up)
• Cognitive Science and Cognitive Neuroscience
• Now distinct from AI
14. Thinking Rationally
• Normative (or prescriptive) rather than
descriptive
• Aristotle: What are correct arguments / thought
processes?
• Logic notation and rules for derivation for
thoughts
• Problems:
• Not all intelligent behavior is mediated by logical
deliberation
• What is the purpose of thinking? What thoughts should I
have?
15. Acting Rationally
• Rational behavior
• Doing the right thing
• What is the “right thing”?
• That which is expected to maximize goal achievement,
given available information
• We do many (“right”) things without thinking
• Thinking should be in the service of rational action
16. Applied Areas of AI
• Heuristic Search
• Computer Vision
• Adversarial Search (Games)
• Fuzzy Logic
• Natural Language Processing
• Knowledge Representation
• Planning
• Learning
17. Concepts to be learned
• Problem-Solving
– Uninformed Search
– Informed Search
• AI and Games
• Machine Learning
• Evolutionary Computation
• Robotics and AI
• Intelligent Agents and Agent-based Modeling
18. Semester Tools
• References as Textbooks:
– Artificial Intelligence a system approach, by M. Tim
Jones, 2008.
– Artificial Intelligence A modern Approach, 3rd
Edition, by Stuart J. Russell and Peter Norving, 2010.