Transcript Document

1. Introduction
Prof. Gheorghe Tecuci
Learning Agents Laboratory
Computer Science Department
George Mason University
 2003, G.Tecuci, Learning Agents Laboratory
1
Overview
What is Artificial Intelligence
What is Machine Learning
History of Machine Learning
Demo: Disciple learning agent
Basic bibliography and reading
 2003, G.Tecuci, Learning Agents Laboratory
2
What is Artificial Intelligence
 2003, G.Tecuci, Learning Agents Laboratory
3
Central goals of Artificial Intelligence
Understand the principles that make intelligence possible
(in humans, animals, and artificial agents)
Developing intelligent machines or agents
(no matter whether they operate as humans or not)
Formalizing knowledge and mechanizing reasoning
in all areas of human endeavor
Making the working with computers
as easy as working with people
Developing human-machine systems that exploit the
complementariness of human and automated reasoning
 2003, G.Tecuci, Learning Agents Laboratory
4
What is an intelligent agent
An intelligent agent is a system that:
• perceives its environment (which may be the physical
world, a user via a graphical user interface, a collection of
other agents, the Internet, or other complex environment);
• reasons to interpret perceptions, draw inferences, solve
problems, and determine actions; and
• acts upon that environment to realize a set of goals or
tasks for which it was designed.
input/
sensors
user/
environment
 2003, G.Tecuci, Learning Agents Laboratory
output/
effectors
Intelligent
Agent
5
Characteristic features of intelligent agents
Knowledge representation and reasoning
Transparency and explanations
Ability to communicate
Use of huge amounts of knowledge
Exploration of huge search spaces
Use of heuristics
Reasoning with incomplete or conflicting data
Ability to learn and adapt
 2003, G.Tecuci, Learning Agents Laboratory
6
Overview
What is Artificial Intelligence
What is Machine Learning
History of Machine Learning
Demo: Disciple learning agent
Basic bibliography and reading
 2003, G.Tecuci, Learning Agents Laboratory
7
What is Machine Learning
 2003, G.Tecuci, Learning Agents Laboratory
8
The architecture of a learning agent
Implements a general problem solving method that uses
the knowledge from the knowledge base to interpret the
input and provide an appropriate output.
Learning Agent
Input/
Sensors
User/
Environment
Problem Solving
Engine
Learning
Engine
Output/
Effectors
Knowledge Base
Ontology
Rules/Cases/Methods
Implements
learning
methods
for extending
and refining
the knowledge
base to
improve
agent’s
competence
and/or
efficiency in
problem
solving.
Data structures that represent the objects from the application domain,
general laws governing them, actions that can be performed with them, etc.
 2003, G.Tecuci, Learning Agents Laboratory
9
What is Learning?
Learning denotes changes in the system that are adaptive
in the sense that they enable the system to do the same
task or tasks drawn from the same population more
effectively the next time (Simon, 1983).
Learning is making useful changes in our minds (Minsky,
1985).
Learning is constructing or modifying representations of
what is being experienced (Michalski, 1986).
A computer program learns if it improves its performance at
some task through experience (Mitchell, 1997).
 2003, G.Tecuci, Learning Agents Laboratory
10
So what is Learning?
Learning is a very general term denoting the way in
which people and computers:
(1) Acquire, discover, and organize knowledge (by
building, modifying and organizing internal
representations of some external reality);
(2) Acquire skills (by gradually improving their motor or
cognitive skills through repeated practice, sometimes
involving little or no conscious thought).
Learning results in changes in the agent (or mind) that
improve its competence and/or efficiency.
 2003, G.Tecuci, Learning Agents Laboratory
11
Two complementary dimensions for learning
Competence
A system is improving its competence if it learns to solve a
broader class of problems, and to make fewer mistakes in
problem solving.
Efficiency
A system is improving its efficiency, if it learns to solve the
problems from its area of competence faster or by using
fewer resources.
 2003, G.Tecuci, Learning Agents Laboratory
12
Main directions of research in Machine Learning
Discovery of general principles, methods,
and algorithms of learning
Automation of the construction
of knowledge-based systems
 2003, G.Tecuci, Learning Agents Laboratory
13
Learning strategies
A Learning Strategy is a basic form of learning characterized by the
employment of a certain type of inference (e.g. deduction, induction
or analogy), a certain type of computational or representational
mechanism (e.g. rules, trees, neural networks, etc.), and a certain
type of learning goal (e.g. learn a concept, discover a formula,
acquire new knowledge about an entity, refine an entity).
• Rote learning
• Instance-based learning
• Learning from instruction
• Reinforcement learning
• Learning from examples
• Neural networks
• Explanation-based learning
• Genetic algorithms and
evolutionary computation
• Conceptual clustering
• Quantitative discovery
• Abductive learning
• Learning by analogy
 2003, G.Tecuci, Learning Agents Laboratory
• Reinforcement learning
• Bayesian learning
• Multistrategy learning
14
Overview
What is Artificial Intelligence
What is Machine Learning
History of Machine Learning
Demo: Disciple learning agent
Basic bibliography and reading
 2003, G.Tecuci, Learning Agents Laboratory
15
History of Machine Learning
Early enthusiasm (1955 - 1965)
• Learning without knowledge;
• Neural modeling (self-organizing systems and decision
space techniques);
• Evolutionary learning;
• Rote learning (Samuel Checker’s player).
 2003, G.Tecuci, Learning Agents Laboratory
16
History of Machine Learning (cont.)
Dark ages (1962 - 1976)
• To acquire knowledge one needs knowledge;
• Realization of the difficulty of the learning process
and of the limitations of the explored methods
(e.g. the perceptron cannot learn the XOR function);
• Symbolic concept learning (Winston’s influential
thesis, 1972).
 2003, G.Tecuci, Learning Agents Laboratory
17
History of Machine Learning (cont.)
Renaissance (1976 - 1988)
• Exploration of different strategies (EBL, CBR, GA, NN,
Abduction, Analogy, etc.);
• Knowledge-intensive learning;
• Successful applications;
• Machine Learning conferences/workshops worldwide.
 2003, G.Tecuci, Learning Agents Laboratory
18
History of Machine Learning (cont.)
Maturity (1988 - present)
• Experimental comparisons;
• Revival of non-symbolic methods;
• Computational learning theory;
• Multistrategy learning;
• Integration of machine learning and knowledge
acquisition;
• Emphasis on practical applications.
 2003, G.Tecuci, Learning Agents Laboratory
19
Successful applications of Machine Learning
• Learning to recognize spoken words (all of the most
successful systems use machine learning);
• Learning to drive an autonomous vehicle on public
highway;
• Learning to classify new astronomical structures (by
learning regularities in a very large data base of image
data);
• Learning to play games;
• Automation of knowledge acquisition from domain
experts;
• Learning agents.
 2003, G.Tecuci, Learning Agents Laboratory
20
Overview
What is Artificial Intelligence
What is Machine Learning
History of Machine Learning
Demo: Disciple learning agent
Basic bibliography and reading
 2003, G.Tecuci, Learning Agents Laboratory
21
Disciple approach to agent development
Disciple is a theory, methodology and agent shell for
rapid development of end to end knowledge bases and
agents, by subject matter experts, with limited assistance
from knowledge engineers
The expert teaches Disciple in a
way that resembles how the
expert would teach a person.
Disciple learns from the expert,
building, verifying and
improving its knowledge base
Interface
DISCIPLE RKF/COG
 2003, G.Tecuci, Learning Agents Laboratory
Problem
Solving
Learning
Ontology
+ Rules
22
Vision on the evolution of the software development process
Mainframe
Computers
Personal
Computers
Learning
Agents
Software systems
developed and used by
persons that are not
computer experts
Software systems developed
by computer experts
and used by persons that
are not computer experts
Software systems
developed and used
by computer experts
 2003, G.Tecuci, Learning Agents Laboratory
23
Vision on the use of Disciple in Education
teaches
Disciple
Agent KB
teaches
Disciple
Agent KB
teaches
…
The expert/teacher teaches Disciple
through examples and explanations,
in a way that is similar to how the
expert would teach a student.
Disciple
Agent KB
Disciple
Agent KB
teaches
Disciple tutors the student in a
way that is similar to how the
expert/teacher has taught it.
 2003, G.Tecuci, Learning Agents Laboratory
24
An intelligent agent for Center of Gravity analysis
The center of gravity of an entity (state, alliance,
coalition, or group) is the foundation of capability,
the hub of all power and movement, upon which
everything depends, the point against which all the
energies should be directed.
Carl Von Clausewitz, “On War,” 1832.
If a combatant eliminates or influences the enemy’s
strategic center of gravity, then the enemy will lose
control of its power and resources and will
eventually fall to defeat. If the combatant fails to
adequately protect his own strategic center of
gravity, he invites disaster.
(Giles and Galvin, USAWC 1996).
 2003, G.Tecuci, Learning Agents Laboratory
25
Approach to Center of Gravity (COG) analysis
• Based on the concepts of critical capabilities, critical requirements and
critical vulnerabilities, which have been recently adopted into the joint
military doctrine of USA (Strange , 1996).
• Applied to current war scenarios (e.g. War on terror 2003, Iraq 2003)
with state and non-state actors (e.g. Al Qaeda).
Identification of COG candidates
Identify potential primary
sources of moral or physical
strength, power and
resistance from:
Government
Military
 2003, G.Tecuci, Learning Agents Laboratory
Testing of COG candidates
Test each identified COG
candidate to determine whether
it has all the necessary critical
capabilities:
Which are the critical
capabilities?
People
Are the critical requirements of
these capabilities satisfied?
Economy
If not, eliminate the candidate.
Alliances
If yes, do these capabilities
have any vulnerability?
Etc.
26
Critical capabilities needed to be a COG
people
leader
be protected
stay informed
communicate
military
receive
communication from
the highest level
leadership
be deployable
communicate desires
to the highest level
leadership
be indispensable
be influential
support the goal
be a driving force
have support
be irreplaceable
 2003, G.Tecuci, Learning Agents Laboratory
exert power
industrial capacity
financial capacity
support the highest
level leadership
external support
have a positive impact
will of multi
member force
be influential
ideology
27
Leader who is a COG
Critical capability to
Corresponding critical requirement
be protected
Have means to be protected from all threats
stay informed
Have means to receive essential intelligence
communicate
Have means to communicate with the
government, the military and the people
be influential
Have means to influence the government, the
military and the people
be a driving force
Have reasons and determination for pursuing
the goal
have support
Have means to secure continuous support from
the government, the military and the people
be irreplaceable
Be the only leader to maintain the goal
 2003, G.Tecuci, Learning Agents Laboratory
28
Illustration: Saddam Hussein (Iraq 2003)
Critical capability to
be protected
Corresponding critical requirement
Have means to be protected from all threats
Means

Vulnerabilities
Republican Guard Protection Unit
 loyalty not based on conviction and can be influenced by US-led coalition
Iraqi Military
 loyalty can be influenced by US-led coalition
 can be destroyed by US-led coalition
Complex of Iraqi Bunkers  location known to US led coalition
 design known to US led coalition
 can be destroyed by US-led coalition
System of Saddam Doubles
 loyalty of Saddam Doubles to Saddam can be influenced by US-led coalition
 2003, G.Tecuci, Learning Agents Laboratory
29
Demonstration
Teaching Disciple how to determine whether a strategic
leader has the critical capability to be protected.
Disciple
Demo
 2003, G.Tecuci, Learning Agents Laboratory
30
Basic bibliography
Mitchell T.M., Machine Learning, McGraw Hill, 1997.
Shavlik J.W. and Dietterich T. (Eds.), Readings in Machine Learning, Morgan Kaufmann,
1990.
Buchanan B., Wilkins D. (Eds.), Readings in Knowledge Acquisition and Learning:
Automating the Construction and the Improvement of Programs, Morgan Kaufmann, 1992.
Langley P., Elements of Machine Learning, Morgan Kaufmann, 1996.
Michalski R.S., Carbonell J.G., Mitchell T.M. (Eds), Machine Learning: An Artificial
Intelligence Approach, Morgan Kaufmann, 1983 (Vol. 1), 1986 (Vol. 2).
Kodratoff Y. and Michalski R.S. (Eds.) Machine Learning: An Artificial Intelligence
Approach (Vol. 3), Morgan Kaufmann Publishers, Inc., 1990.
Michalski R.S. and Tecuci G. (Eds.), Machine Learning: A Multistrategy Approach (Vol. 4),
Morgan Kaufmann Publishers, San Mateo, CA, 1994.
Tecuci G. and Kodratoff Y. (Eds.), Machine Learning and Knowledge Acquisition:
Integrated Approaches, Academic Press, 1995.
Tecuci G., Building Intelligent Agents: An Apprenticeship Multistrategy Learning
Theory, Methodology, Tool and Case Studies, Academic Press, 1998.
 2003, G.Tecuci, Learning Agents Laboratory
31
Recommended reading
Mitchell T.M., Machine Learning, Chapter 1: Introduction, pp. 1-19, McGraw
Hill, 1997.
Tecuci G., Boicu M., Marcu D., Stanescu B., Boicu C., Comello J., Training
and Using Disciple Agents: A Case Study in the Military Center of Gravity
Analysis Domain, in AI Magazine, 24, 4, 2002, pp.51-68, AAAI Press,
Menlo Park, California, 2002, http://lalab.gmu.edu/publications/default.htm
 2003, G.Tecuci, Learning Agents Laboratory
32