Sei sulla pagina 1di 17

Artificial Intelligence

Lecture #11

Dr. Md. Hasanuzzaman


Associate Professor
Department of Computer Science & Engineering
Dhaka University

October 14, 2008 Artificial Intelligence, Lecturer #11 1


Contents
 Knowledge Acquisition
 Machine Learning
 Types of Learning
 General Learning Model
 Factors Affecting Learning Performance
 Performance Measures

October 14, 2008 Artificial Intelligence, Lecturer #11 2


Knowledge Acquisition

 The process of acquiring, studying and organizing


knowledge, so that it can be used in a knowledge-
based system.
 Expert may also provide irrelevant, incomplete or
inconsistent information.
 Data and knowledge acquisition
 Collect and analyze data and knowledge
 Make key concepts of the system design more explicit

October 14, 2008 Artificial Intelligence, Lecturer #11 3


Knowledge Acquisition (Cont.)
 Acquired knowledge may consist facts, rules,
concept, procedures, heuristics, formulas,
relationships, statistics, or other useful information
 Sources of this knowledge are:
 Experts in the domain of interest
 Textbooks
 Technical Papers
 Databases
 Reports
 The environment

October 14, 2008 Artificial Intelligence, Lecturer #11 4


Machine Learning

 Machine learning is a specialized form of autonomous


knowledge acquisition.
 Autonomous knowledge creation or refinement through
the use of computer programs.

October 14, 2008 Artificial Intelligence, Lecturer #11 5


Types of Learning

 Learning by memorization
 Direct instruction

 Analogy

 Induction

 Deduction

October 14, 2008 Artificial Intelligence, Lecturer #11 6


Learning by Memorization

 It requires the least amount of inference and


is accomplished by simply copying the
knowledge in the same form that it will be
used directly into the knowledge base.

October 14, 2008 Artificial Intelligence, Lecturer #11 7


Learning by Direct Instruction

 The knowledge must be transformed into an


operational form before being integrated into
the knowledge base
 This type of learning used when a teacher
presents a number of facts directly to us in a
well organized manner.

October 14, 2008 Artificial Intelligence, Lecturer #11 8


Analogical Learning

 Isthe process of learning a new concept or


solution through the use of similar known
concepts or solutions.
 Here, previously learn examples serve as a guide.

 Driving a truck using experience of driving a car.

October 14, 2008 Artificial Intelligence, Lecturer #11 9


Learning by Induction

 This form of learning requires the use of inductive


inference
 We use inductive learning when we formulate a
general concept after seeing a number of instances
or examples of the concept.
 Example: we learn the concepts of color or sweet
taste after experiencing the sensations associated
with several examples of color example objects or
sweet foods
October 14, 2008 Artificial Intelligence, Lecturer #11 10
Deductive Learning

 It is accomplished through a sequence of deductive


inference steps using known facts.
 From the known facts, new facts and relationships
are logically derived.
 Example:(father X of Y), (father Y of Z);
Grandfather X of Z)

October 14, 2008 Artificial Intelligence, Lecturer #11 11


General Learning Model
Stimuli
Examples
Li Feedback
Learner
Component

Critic
Knowledge
Environment performance
base
/Teacher evaluator
Response
Performance
Component
Tasks

October 14, 2008 Artificial Intelligence, Lecturer #11 12


General Learning Model (Cont.)
 Inputs to the learner component may be physical stimuli of
some type or descriptive, symbolic training examples
 The information conveyed to the learner component is used
to create and modify knowledge structures in the knowledge
base
 This knowledge is used by the performance component to
carry out some tasks, such as solving a problem.
 The performance module produces a response describing its
actions in performing task
 The critic module evaluates this response relative to an
optimal response
 Feedback, indicating whether or not the performance was
acceptable.
October 14, 2008 Artificial Intelligence, Lecturer #11 13
Factors Affecting Learning
Performance
 Factors which affect the performance of a learner
system include:
The representation scheme used
The training scenarios
The type of feedback
Background knowledge
The learning algorithm

October 14, 2008 Artificial Intelligence, Lecturer #11 14


Performance Measures
 Performance measures provide a means of comparing different
performance characteristics of learning algorithms. Some of the
important parameters are:
 Generality: is the method can be adapted to different domains
of application.
 Efficiency: is measure the average time required to construct
the target knowledge structures from some specified initial
structure
 Robustness: how it work against noise (noisy feedback, data)
 Efficacy: combination of generality, efficiency, robustness
 Edge of implementation: relates the complexity of the programs
and data structures and the resources required to develop the
given learning system.
October 14, 2008 Artificial Intelligence, Lecturer #11 15
Recommended Textbooks
 [Negnevitsky, 2001] M. Negnevitsky “ Artificial
Intelligence: A guide to Intelligent Systems”, Pearson
Education Limited, England, 2002.
 [Russel, 2003] S. Russell and P. Norvig Artificial
Intelligence: A Modern Approach Prentice Hall, 2003,
Second Edition
 [Patterson, 1990] D. W. Patterson, “Introduction to Artificial
Intelligence and Expert Systems”, Prentice-Hall Inc.,
Englewood Cliffs, N.J, USA, 1990.
 [Lindsay, 1997] P. H. Lindsay and D. A. Norman, Human
Information Processing: An Introduction to Psychology,
Academic Press, 1977.
October 14, 2008 Artificial Intelligence, Lecturer #11 16
End of Presentation

Question/Suggestions?

Thanks to all !!!

October 14, 2008 Artificial Intelligence, Lecturer #11 17

Potrebbero piacerti anche