ICT619 Intelligent Systems
Download
Report
Transcript ICT619 Intelligent Systems
ICT619 Intelligent
Systems
Unit Coordinator:
Graham Mann
Room 2.061 ECL Building
Phone: 9360 7270
Email: [email protected]
Unit aims
to be aware of the rationale of the artificial intelligence
and soft computing paradigms with their advantages
over traditional computing
to gain an understanding of the theoretical foundations
of various types of intelligent systems technologies to a
level adequate for achieving objectives as stated below
to develop the ability to evaluate intelligent systems,
and in particular, their suitability for specific
applications
to be able to manage the application of various tools
available for developing intelligent systems
2
Unit delivery and learning
structure
3 hours of lecture/workshop per week
Lecture/WS time will be spent discussing the relevant
topic after an introduction by the lecturer
Topic lecture notes will be available early in the week
Students should make use of the topic reading material
in advance for the topic to be covered
Bringing up issues and questions for discussion are
encouraged to create an interactive learning
environment (this is assessed).
3
Resources and Textbooks
Main text:
Negnevitsky, M. Artificial Intelligence: A Guide to
Intelligent Systems, 2005. 2nd Edition.
The main text to be supplemented by chapters/articles
from other books/journals/magazines as well as notes
provided by the unit coordinator.
A list of recommended readings and other resources
will be provided for each topic.
Unit website:
http://www.it.murdoch.edu.au/units/ICT619 will
enable access to unit reading materials and links to
other resources.
4
Assessment
ACTIVITY
DUE
WEIGHT
Workshop
participation
Continuous
10%
Project
Week 12
35%
Closed-book
Exam
Nov exams period
55%
5
Topic schedule
Topic 1:
Topic 2:
Topic 3:
Topic 4:
Topic 5:
Topic 6:
Topic 7:
Topic 8:
Topic 9:
Introduction to Intelligent Systems:
Tools, Techniques and Applications
Rule-Based Expert Systems
Fuzzy Systems
Neural Computing
Genetic Algorithms
Case-based Reasoning
Data Mining
Intelligent Software Agents
Language Technology
6
Topic 1: Introduction to Intelligent
Systems
What is an intelligent system?
Significance of intelligent systems in business
Characteristics of intelligent systems
The field of Artificial Intelligence (AI)
The Soft Computing paradigm
An Overview of Intelligent System Methodologies
Expert Systems
Fuzzy Systems
Artificial Neural Networks
Genetic Algorithms (GA)
Case-based reasoning (CBR)
Data Mining
Intelligent Software Agents
Language Technology
7
What is an intelligent system?
What is intelligence?
Hard to define unless you list characteristics eg,
Reasoning
Learning
Adaptivity
A truly intelligent system adapts itself to deal with
changes in problems (automatic learning)
Few machines can do that at present
Machine intelligence has a computer follow problem
solving processes something like that in humans
Intelligent systems display machine-level intelligence,
reasoning, often learning, not necessarily self-adapting
8
Intelligent systems in business
Intelligent systems in business utilise one or more intelligence
tools, usually to aid decision making
Provides business intelligence to
Increase productivity
Gain competitive advantage
Examples of business intelligence – information on
Customer behaviour patterns
Market trend
Efficiency bottlenecks
Examples of successful intelligent systems applications in
business:
Customer service (Customer Relations Modelling)
Scheduling (eg Mine Operations)
Data mining
Financial market prediction
Quality control
9
Intelligent systems in business –
some examples
HNC (now Fair Isaac) software’s credit card fraud detector Falcon
offers 30-70% improvement over existing methods (an example of
a neural network).
MetLife insurance uses automated extraction of information from
applications in MITA (an example of language technology use)
Personalized, Internet-based TV listings (an intelligent agent)
Hyundai’s development apartment construction plans FASTrak-Apt
(a Case Based Reasoning project)
US Occupational Safety and Health Administration (OSHA uses
"expert advisors" to help identify fire and other safety hazards at
work sites (an expert system).
Source: http://www.newsfactor.com/perl/story/16430.html
10
Characteristics of intelligent
systems
Possess one or more of these:
Capability to extract and store knowledge
Human like reasoning process
Learning from experience (or training)
Dealing with imprecise expressions of facts
Finding solutions through processes similar to natural evolution
Recent trend
More sophisticated Interaction with the user through
natural language understanding
speech recognition and synthesis
image analysis
Most current intelligent systems are based on
rule based expert systems
one or more of the methodologies belonging to soft computing
11
The field of Artificial Intelligence (AI)
Primary goal:
Development of software aimed at enabling machines to solve
problems through human-like reasoning
Attempts to build systems based on a model of knowledge
representation and processing in the human mind
Encompasses study of the brain to understand its structure and
functions
In existence as a discipline since 1956
Failed to live up to initial expectations due to
inadequate understanding of intelligence, brain function
complexity of problems to be solved
Expert systems – an AI success story of the 80s
Case Based Reasoning systems - partial success
12
The Soft Computing (SC) paradigm
Also known as Computational Intelligence
Unlike conventional computing, SC techniques
1. can be tolerant of imprecise, incomplete or corrupt input data
2. solve problems without explicit solution steps
3. learn the solution through repeated observation and
adaptation
4. can handle information expressed in vague linguistic terms
5. arrive at an acceptable solution through evolution
13
The Soft Computing (SC) paradigm
(cont’d)
The first four characteristics are common in
problem solving by individual humans
The fifth characteristic (evolution) is common in
nature
The predominant SC methodologies found in
current intelligent systems are:
Artificial Neural Networks (ANN)
Fuzzy Systems
Genetic Algorithms (GA)
14
Overview of Intelligent System
Methodologies
- Expert Systems (ES)
Designed to solve problems in a specific domain,
eg, an ES to assist foreign currency traders
Built by
interrogating domain experts
storing acquired knowledge in a form suitable for solving
problems, using simple reasoning
Used by
Querying the user for problem-specific information
Using the information to draw inferences from the knowledge
base
Supplies answers or suggested ways to collect further inputs
15
Overview of Expert Systems (cont’d)
Usual form of the expert system knowledge
base is a collection of IF … THEN … rules
Note: not IF statements in procedural code
Some areas of ES application:
banking and finance (credit assessment, project
viability)
maintenance (diagnosis of machine faults)
retail (suggest optimal purchasing pattern)
emergency services (equipment configuration)
law (application of law in complex scenarios)
16
Artificial Neural Networks (ANN)
Human brain consists of 100 billion densely interconnected simple
processing elements known as neurons
ANNs are based on a simplified model of the neurons and their
operation
ANNs usually learn from experience – repeated presentation of
example problems with their corresponding solutions
After learning the ANN is able to solve problems, even with newish
input
The learning phase may or may not involve human intervention
(supervised vs unsupervised learning)
The problem solving 'model' developed remains implicit and
unknown to the user
Particularly suitable for problems not prone to algorithmic
solutions, eg, pattern recognition, decision support
17
Artificial Neural Networks (cont’d)
Different models of ANNs depending on
Architecture
learning method
other operational characteristics (eg type of activation function)
Good at pattern recognition and classification problems
Major strength - ability to handle previously unseen, incomplete or
corrupted data
Some application examples:
- explosive detection at airports
- face recognition
- financial risk assessment
- optimisation and scheduling
18
Genetic Algorithms (GA)
Belongs to a broader field known as evolutionary computation
Solution obtained by evolving solutions through a process
consisting of
survival of the fittest
crossbreeding, and
mutation
A population of candidate solutions is initialised (the
chromosomes)
New generations of solutions are produced beginning with the
intial population, using specific genetic operations: selection,
crossover and mutation
19
Genetic Algorithms (cont’d)
Next generation of solutions produced from the current population
using
crossover (splicing and joining peices of the solution from parents) and
mutation (random change in the parameters defining the solution)
The fitness of newly evolved solution evaluated using a fitness
function
The steps of solution generation and evaluation continue until an
acceptable solution is found
GAs have been used in
portfolio optimisation
bankruptcy prediction
financial forecasting
design of jet engines
scheduling
20
Fuzzy Systems
Traditional logic is two-valued – any proposition is
either true or false
Problem solving in real-life must deal with partially true
or partially false propositions
Imposing precision may be difficult and lead to less
than optimal solutions
Fuzzy systems handle imprecise information by
assigning degrees of truth - using fuzzy logic
21
Fuzzy Systems (cont’d)
FL allow us to express knowledge in vague linguistic
terms
Flexibility and power of fuzzy systems now well
recognised (eg simplification of rules in control systems
where imprecision is found)
Some applications of fuzzy systems:
Control of manufacturing processes
appliances such as air conditioners, washing machines and
video cameras
Used in combination with other intelligent system
methodologies to develop hybrid fuzzy-expert, neuro-fuzzy,
or fuzzy-GA systems
22
Case-based reasoning (CBR)
CBR systems solve problems by making use of knowledge about
similar problems encountered in the past
The knowledge used in the past is built up as a case-base
CBR systems search the case-base for cases with attributes
similar to given problem
A solution created by synthesizing similar cases, and adjusting to
cater for differences between given problem and similar cases
Difficult to do well in practice, but very powerful if you can do it
23
Case-based reasoning (cont’d)
CBR systems can improve over time by learning from
mistakes made with past problems
Application examples:
Utilisation of shop floor expertise in aircraft repairs
Legal reasoning
Dispute mediation
Data mining
Fault diagnosis
Scheduling
24
Data mining
The process of exploring and analysing data for
discovering new and useful information
Huge volumes of mostly point-of-sale (POS) data are
generated or captured electronically every day, eg,
data generated by bar code scanners
customer call detail databases
web log files in e-commerce etc.
Organizations are ending up with huge amounts of
mostly day-to-day transaction data
25
Data mining (cont’d)
It is possible to extract useful information on market and customer
behaviour by “mining" the data
Note: This goes far beyond simple statistical analysis of numerical
data, to classification and analysis of non-numerical data
Such information might
reveal important underlying trends and associations in market
behaviour, and
help gain competitive advantage by improving marketing
effectiveness
Techniques such as artificial neural networks and decision trees
have made it possible to perform data mining involving large
volumes of data (from "data warehouses").
Growing interest in applying data mining in areas such direct
target marketing campaigns, fraud detection, and development of
models to aid in financial predictions, antiterrorism systems
26
Intelligent software agents (ISA)
ISAs are computer programs that provide active assistance to
information system users
Help users cope with information overload
Act in many ways like a personal assistant to the user by
attempting to adapt to the specific needs of the user
Capable of learning from the user as well as other intelligent
software agents
Application examples:
News and Email Collection,
Filtering and Management
Online Shopping
Event Notification
Personal scheduling
Online help desks, interactive characters
Rapid Response Implementation
27
Language Technology (LT)
“[The] application of knowledge about human language in computerbased solutions” (Dale 2004)
Communication between people and computers is an important
aspect of any intelligent information system
Applications of LT:
Natural Language Processing (NLP)
Knowledge Representation
Speech recognition
Optical character recognition (OCR)
Handwriting recognition
Machine translation
Text summarisation
Speech synthesis
A LT-based system can be the front-end of
information systems themselves based on
other intelligence tools
Hi, I am Cybelle.
What is your name?
28
For Next Week
Get hold of the textbook
Visit the library and find the section on
artificial intelligence, browse some titles
Get onto the unit website, download and
read papers concerning Expert Systems
We will study the theory and practice
developing a simple expert system
Have a look at the AAAI Applications
webpage at
http://www.aaai.org/AITopics/html/applications.html
29