You are on page 1of 20

Introduction

Artificial Intelligent
Intelligent Systems
ELE 4643
Course Overview
The course is an introductory survey of
Intelligent Systems. It starts by a brief
introducing of Artificial Intelligence with
applications and tools such as Expert Systems
and simple Search methods.
Machine learning (a current topic) will be
introduced next followed by Artificial Neural
Networks (LO3), Fuzzy Systems (LO2) and
Genetic Algorithms( LO4).
Course Learning Outcomes
 LO1: Introduction to AI and Machine
Learning
 LO3: Artificial Neural Networks
 LO2: Fuzzy Systems
 LO4: Genetic algorithms
What is Intelligence ?
 There is no agreement on the definition of
human intelligence among scientists.
 One definition that suits our purpose is:
“ intelligence is the ability to learn and
understand, to solve problems and to make
decisions”
Goals Of Artificial Intelligence
 The goal of artificial intelligence (AI) as a science
is to make machines do things that would require
intelligence if done by humans..
 The traditional problems (or goals) of AI research
include reasoning, knowledge representation,
planning, learning, natural language processing,
vision, perception and the ability to move and
manipulate objects. Wikipedia
What is AI ?
Video
Modern AI
 Modern machine capabilities generally
classified as AI include successfully
understanding human speech, competing at
the highest level in strategic game systems,
autonomously operating cars, intelligent
routing in content delivery networks, and
military simulations.
AI & Machine Learning
Turing Test
 A Turing Test is a method of inquiry in
artificial intelligence (AI) for determining
whether or not a computer is capable of
thinking like a human being. The test is
named after Alan Turing, the founder of
the Turning Test and an English computer
scientist.
Turing Imitation Game
Turing Test
 A person is placed in one room and a
computer/robot programmed to deceive the
interrogator in another room. The robot would
be programmed to make mistakes and provide
fuzzy answers in the way a human would. If
the computer can fool the interrogator to think
it is a real person, then the computer has
passed the intelligent behavior test.
Expert Systems
 In artificial intelligence, an expert system is a computer
system that emulates the decision-making ability of a
human expert.
 Expert systems are designed to solve complex problems
by reasoning through bodies of knowledge, represented
mainly as if–then rules .
 The first expert systems were created in the 1970s and
then popularized in the 1980s.
 Expert systems were among the first truly successful
forms of artificial intelligence (AI) applications.
Expert Systems Functions
 Store expertise information from an expert
in a machine.

 Explain reasoning or suggested decisions


 Display intelligent behavior
 Draw conclusions from complex relationships
 Provide portable knowledge
When to Use an Expert System
 Capture and preserve irreplaceable human
expertise
 Provide expertise needed at a number of
locations at the same time
 Works in hostile environments that are
dangerous to human health
When to Use an Expert System
 Provide expertise that is expensive or rare
 Develop a solution faster than human
experts can
 Provide expertise needed for training and
development to share the wisdom of human
experts with a large number of people
Components of an
Expert System
 Knowledge base
 Stores all relevant information, data, rules, cases, and
relationships used by the expert system
 Inference engine
 Seeks information and relationships from the
knowledge base and provides answers, predictions,
and suggestions in the way a human expert would
 Rule
 A conditional statement that links given conditions to
actions or outcomes
Inference: Reasoning Methods
 Fuzzy logic
 Allows fuzzy reasoning and shades of gray and does
not require everything to be simply yes/no, or
true/false
 Backward chaining
 A method of reasoning that starts with conclusions and
works backward to the supporting facts
 Forward chaining
 A method of reasoning that starts with the facts and
works forward to the conclusions Schematic
Explanation Inference
facility engine

Knowledge
Knowledge base User
base acquisition interface
facility

Experts User
Simple Expert System:
Loan Application
Mortgage application for a loan for $100,000 to $200,000

If there are no previous credits problems, and


If month net income is greater than 4x monthly loan payment, and
If down payment is 15% of total value of property, and
If net income of borrower is > $25,000, and
If employment is > 3 years at same company

Then accept the applications

Else check other credit rules


Simple Search Problem solver
 The simplest view of AI systems is as a search
problem solver. Google ..It is almost impossible
to develop an expert system without
implementing some search technique or another
to navigate through the problem domain for the
solution. Search techniques provide the base for
the inference engine, which is an essential
component of any expert system.

You might also like