1. TECHNOLOGY GUIDE FOUR
Intelligent Systems

2. TECHNOLOGY GUIDE OUTLINE
TG4.1 Introduction to Intelligent Systems TG4.2 Expert Systems TG4.3 Neural Networks TG4.4 Fuzzy Logic TG4.5 Genetic Algorithms TG4.6 Intelligent Agents

3. LEARNING OBJECTIVES
1. Differentiate between artificial intelligence and human intelligence. 2. Define expert systems, and provide examples of their use. 3. Define neural networks, and provide examples of their use. 4. Define fuzzy logic, and provide examples of its use.

4. LEARNING OBJECTIVES (continued)
5. Define genetic algorithms, and provide examples of their use. 6. Define intelligent agents, and provide examples of their use.

5. TG4.1 Introduction to Intelligent Systems
Intelligent systems Artificial intelligence (AI)
Intelligent systems is a term that describes the various commercial applications of AI.
Artificial intelligence (AI) is a subfield of computer science concerned with:
* studying the thought processes of humans
* recreating those processes via machines, such as computer and robots.
© Luis Alonso Ocana/Age Fotostock America, Inc.

6. TG 4.2 Expert Systems Expertise Expert systems (ESs)
Expertise refers to the extensive, task-specific knowledge acquired from training, reading
and experience.
Expert systems (ESs) attempt to mimic human experts by applying expertise in a specific
domain. Can support decision makers or completely replace them.

7. Expertise Transfer from Human to Computer
Knowledge acquisition Knowledge representation Knowledge inferencing Knowledge transfer
Knowledge acquisition: Knowledge is from experts or from documented sources.
Knowledge representation: Acquired knowledge is organized as rules or frames
(objective-oriented) and stored electronically in a knowledge base.
Knowledge inferencing: Given the necessary expertise stored in the knowledge base,
the computer is programmed so that it can make inferences. The reasoning function is
performed in a component called the inference engine, which is the brain of ES.
Knowledge transfer: The inferenced expertise is transferred to the user in the form of
a recommendation.

8. The Components of Expert Systems
Knowledge base Inference engine User interface Blackboard Explanation subsystem
Knowledge base contains knowledge necessary for understanding, formulating and solving problems.
Inference engine is a computer program that provides a methodology for reasoning and formulating conclusions.
User interface enables users to communicate with the computer
Blackboard is an area of working memory set aside for the description of a current problem.
Explanation subsystem explains its recommendations.

9. TG4.3 Neural Network
Neural network is a system of programs and data structures that approximates the operation of the human brain.
Neural networks are particularly good at recognizing subtle, hidden and newly emerging patterns within complex data as well as interpreting incomplete inputs.

10. TG 4.5 Genetic Algorithms
Genetic algorithms have three functional characteristics:
• Selection
• Crossover:
• Mutation:
A genetic algorithm mimics the evolutionary, “survival of the fittest” process to
generate increasingly better solutions to a problem

11. TG 4.6 Intelligent Agents
Information Agents Monitoring-and-Surveillance Agents User Agents
Information agents search for information and display it to users.
Monitoring and surveillance agents constantly observe and report on some item of interest.
User agents take action on a user’s behalf.