Download Slide 1

ARTIFICIAL INTELLIGENCE
[INTELLIGENT AGENTS PARADIGM]
INTRODUCTION
Professor Janis Grundspenkis
Riga Technical University
Faculty of Computer Science and Information Technology
Institute of Applied Computer Systems
Department of Systems Theory and Design
E-mail: [email protected]
Why Would You Study
Artificial Intelligence? (1)
• Artificial intelligence is quickly emerging from the
laboratory and is venturing into the commercial
marketplace. Its impact on society is growing
rapidly: in speech and language technology,
strategic planning and diagnosis, process and
system control, vision and authentication
systems, information retrieval and data-mining
and many other contexts. The many new
realizations continually redefine which
applications we can achieve and push existing
technology to its limits
Why Would You Study
Artificial Intelligence? (2)
• Reasoning with knowledge is a central issue.
The mere fact that knowledge is power makes
the importance of AI indisputable
• Due to the rapidly expanding role of AI in our
current and future society, there is an urgent
need for academically trained people with the
variety of backgrounds who are familiar with the
fundamentals of AI, aware of its reasonable
expectations, and have practical experience in
solving AI problems
Text Books
• Russell S., Norvig P. Artificial Intelligence.
A Modern Approach, Pearson Education,
2010
• Wooldridge M. An Introduction to
MultiAgent Systems, John Wiley and
Sons, 2009
• Hadzic M., et al. Ontology-Based MultiAgent Systems, Springer-Verlag, 2009
What Is Artificial Intelligence? (1)
WHAT IS INTELLIGENCE?
• It is only a word that people use to name
those unknown processes with which our
brains solve problems we call hard
(Minsky)
• Working definitions of what intelligence is
must necessarily change through the
years. We deal with a moving target
which makes it difficult to explain just what
it is we do
What Is Artificial Intelligence? (2)
• In principle, we should be able to build intelligent
machines someday because our brains
themselves are machines!
• One problem is that we know very little about
how the brain actually works
• Even though we do not understand how the
brain performs many mental skills, we can still
work toward making machines that do the same
or similar things
• Artificial Intelligence is simple the name we
give to that kind of research
Different
Approaches to AI (1)
• SYSTEMS THAT ACT LIKE
HUMANS
– The act of creating machines that
perform functions that require
intelligence when performed by people
(Kurzweil, 1990)
– The study of how to make computers
do things at which, at the moment,
people are better
(Rich and Knight, 1991)
Different
Approaches to AI (2)
• SYSTEMS THAT THINK LIKE HUMANS
– The existing new effort to make computer
think … machines with minds, in the full and
literal sense
(Haugeland, 1985)
– The automation of activities that we associate
with human thinking, activities such as
decision-making, problem solving, learning …
(Bellman, 1978)
Different
Approaches to AI (3)
• SYSTEMS THAT THINK
RATIONALLY
– The study of mental faculties through
the use of computational models
(Charniak and McDermont, 1985)
– The study of the computations that
make it possible to perceive, reason and
act
(Winston, 1992)
Different
Approaches to AI (4)
• SYSTEMS THAT ACT RATIONALLY
– Computational intelligence is the
study of the design of intelligent agents
(Poole et al., 1998)
– AI … is concerned with intelligent
behavior in artifacts
(Nilsson, 1998)
Acting Humanly (1)
• THE TURING TEST APPROACH
– The Turing test, proposed by Alan Turing
(1950), was designed to provide a satisfactory
operational definition of intelligence
– The computer would need to possess the
following capabilities:
• Natural language processing
• Knowledge representation
• Automated reasoning
• Machine learning
Acting Humanly (2)
• THE TOTAL TURING TEST
–The computer additionally would
need the following capabilities:
• Computer vision
• Robotics
Thinking Humanly
• THE COGNITIVE MODELING APPROACH
– We need to get inside the actual working of human
minds
• Through introspection - trying to catch our own
thoughts as they go by
• Through psychological experiments to have a
sufficiently precise theory of the mind
• COGNITIVE SCIENCE brings together computer
models from AI and experimental techniques
from psychology
Thinking Rationally
• THE "LAWS OF THOUGHT" APPROACH
– Aristotle syllogisms provided patterns for argument structures
that always yielded correct conclusions when given correct
premises
– Logicians in the 19th century developed a precise notation for
statements about all kinds of things in the world and about the
relations among them
• TWO MAIN OBSTACLES TO THIS APPROACH
– It is not easy to take informal knowledge and state it in the
formal terms required by logical notation
– There is a big difference between being able to solve a problem
"in principle" and doing so in practice
Acting Rationally
• THE RATIONAL AGENT APPROACH
– The agent is just something that acts (agents comes
from the Latin agere, “to do”)
– A rational agent is one that acts so as to achieve the
best outcome or, when there is uncertainty, the best
expected outcome
• ALL THE SKILLS NEEDED FOR THE TURING
TEST ARE THERE TO ALLOW RATIONAL
ACTIONS
• THE STUDY OF AI AS RATIONAL AGENT
DESIGN IS MORE GENERAL APPROACH
Two Complementary Views
of AI
• One as an engineering discipline
concerned with the creation of intelligent
machines
• One as an empirical science concerned
with the computational modeling of human
intelligence
• Former characterizes modern AI, while
the later characterizes modern cognitive
science
Specialties
Which Originated in AI
•
•
•
•
•
•
•
•
•
•
•
•
Robotics
Pattern Recognition
Expert Systems
Automatic Theorem Proving
Cognitive Psychology
Word Processing
Machine Vision
Knowledge Engineering
Computational Linguistics
Symbolic Applied Mathematics
Intelligent Agent Paradigm
Programming Paradigms
Paradigm Shift (1)
• The science of artificial intelligence from its inception
through to the present day is based on
– the reliance on logic as a way of representing
knowledge
– logical inference (logical reasoning) as the primary
mechanism for intelligent reasoning
• This way of looking at knowledge, language, and thought
reflects the rationalist tradition of western philosophy
• It also reflects the underlying assumptions of Turing
test, practically its emphasis on symbolic reasoning, as
a test of intelligence, and the belief that a straightforward
comparison with human behavior was adequate to
confirming machine intelligence
Paradigm Shift (2)
• The later half of the twentieth century has seen
numerous challenges to rationalist philosophy
– various forms of philosophical relativism
question the objective basis of language,
science, society, and thought (Wittgenstein’s,
Husserl’s, Heidegger’s philosophy; Godel’s
and Turing’s views on the very foundations of
mathematics)
– post-modern thought has changed our
understanding of meaning and value in the
arts and society
Paradigm Shift (3)
• New (alternative) models of intelligence
– neural models of intelligence emphasize the brain’s
ability to adapt to the world in which it is situated by
modifying the relationships between individual
neurons
– work in artificial life and genetic algorithms applies
the principles of biological evolution to the problems
of finding solutions to difficult problems
– social systems provide another metaphor for
intelligence in that they exhibit global behavior that
enable them to solve problems that would confound
any of their individual members
Paradigm Shift (4)
TWO THEMES
• First theme is that the view of
intelligence is rooted in culture and
society, and, as a consequence,
emergent
• Second theme is that intelligence is
reflected by the collective behaviors of
large number of very simple interacting
semi-autonomous individuals, or agents
Paradigm Shift (5)
THE MAIN THEMES SUPPORTING
AN AGENT-ORIENTED AND EMERGENT
VIEW OF INTELLIGENCE
• Agents are autonomous or semi-autonomous
• Agents are situated in their environments
• Agents are interactional (they may be seen as a society)
• The society of agents is structured (individual agents
are coordinated with other agents in the overall problem
solving)
• The phenomenon of intelligence in the environment is
emergent (overall cooperative result of the society of agents
can be viewed as greater than the sum of its individual
contributors)