Google
 

Friday, December 21, 2007

Knowledge in Artificial Intelligence


Genetic Algorithms
Genetic algorithms have been applied to many large scale
combinatorial mathematical programming problems such as large scale
scheduling problems and even to producing police sketches of
criminals.
 Knowledge in Artificial Intelligence
As per Sowa, "Knowledge encompasses the implicit and explicit
restrictions placed upon objects, operations, and relationship along with
general and relationships along with general and specific heuristics and
inference procedures involved in the situation being modeled.
Knowledge is now recognized as a major organization resource. Data,
information, and knowledge can be classified by their degree of
abstraction and by their quantity.
Knowledge is the most abstract and exist in the smallest quantity.
 Uses of Knowledge
It can use knowledge given to it b human experts. Such knowledge
consists of facts, concepts, theories, heuristic methods, procedures
and relationships.
The collection of knowledge related to a problem used in AI system is
organized together and it is called a knowledge base.
Once a knowledge base is built, AI techniques are used to give the
computer inference capability based on the facts and relationships
contained in the knowledge base.
 Types of Knowledge based Decision support system
The knowledge component enables a wider range of decisions.
It extends the capabilities of computers well beyond based and model
based DSS.
 Intelligent decision support system
Several models of intelligent DSS were developed over the years.
 Active (Symbiotic) DSS
The DSS executes computations, presents data, and responds to
standard commands.
The DSS should be able to take initiative, or should be able to respond
to nonstandard requests and commands. This type of DSS is called
active or symbiotic DSS.
 User Interface and Decision Visualization
The key to successful use of any DSS is the user interface.
The user interface is the hardware and software that facilitate
communication and interaction between the user and the computer.
User interface area, the subset of the field called human computer
interaction, which is the study of the people, computer technology and the
ways these interact.
The interface includes responses and involves an exchange of graphics,
acoustics, tactile and other means of communication.
Physical aspects of the user interface include…
Input Device _ Mouse, Microphone or keyboard
Output (Display) Device… Monitor, Printer or Speaker
The user formulates a response and takes an action.
The cyclic process shown consists of the following components.
Knowledge It is the information the user must have communicate with the
computer.
Dialog It is an observable series of interchanges or interactions
between the user and the computer.
Action Language This can take various forms, ranging from selecting an item from
the menu to answering a question, moving a display window or
typing command.
Input devices are used to execute actions.
Computer This interprets the user’s action, executes a task and generates
a display
.
Presentation
Language
This is the information displayed to the user via output devices.
Such information can be shown as display menus, windows or
texts.
It can be static or dynamic, numeric or symbolic.
It can appear visually on the monitor, presented as voice or a
printout.
User reaction The user interprets the display, processes the content and plans
an action.
The following are the some of the important issues in building a users
interface. These issues are handled in user interface management system
(UIMS).
Choice of the input & output devices Information density
Screen design Use of icons and symbols
Human machine interaction sequences Information display format
Use of colors and shading
 User Interface Management System (UIMS)
The UIMS also accommodates the action language that enables the
computer inputs and outputs in the form of dialing language or processes.
 Interface Models / Styles
The combination of presentation and action language is called interface
mode.
The interface model determines how information is entered and
displayed.
Following are the different models.
1) Menu Interaction 6) Neural Language
2) Pull down menus 7) Graphical user interface
3) Command language 8) Hybrid modes
4) Question and Answers 9) Graphics
5) Form Interaction 10) Graphic software
 Menu Interaction
In this mode the user selects an item from a list of possible choices for
the function to be performed.
A menu can have sub menus.
Example_ Menu such as file, edit, view, etc.
 Pull down menus
A pull down menu is a submenu that appears as superimposed drop
down menu on the screen usually after an entry has been made in a
higher level menu.
Windows based software makes extensive use of pull down menus.
 Command languages
In this the user enters a command such as run or plot.
Many commands are composed of verb-noun combination such as plot
scales.
Another way to simplify commands is to use macros.
Commands can also entered by voice.
 Question & Answers
This mode begins with the computer asking the user a question.
The user answers the question with a phrase or a sentence or by
selecting an icon in the menu.
Expert systems are the best example for this type.
 Form interaction
In this the user enters data or commands into designated space called
forms.
 Natural Language
A human computer interaction that is similar to human dialog is called
natural language.

No comments: