PC AI - Glossary of Terms (Subjects N-O)

Where Intelligent Technology Meets the Real World

Home

Contents

News

Services

Contact PC AI

Glossary of Terms

Subjects N-O

To Glossary Subject M									To Glossary Subjects P-S

Natural Language Processing

Computational Linguistics	The engineering of systems that process or analyze written or spoken natural language.
	For More Info on Natural Language Processing

Neural Networks

Adaptive Resonance Theory	A two-layer neural net architecture in which information reverberates back and forth between the layers.
Backpropagation	A multilayer feedforward neural net architecture which uses the supervised mode of learning. This is the most widely used type of neural net.
Hidden Layer	A layer of processing elements between a neural network's input layer and its output layer.
Input Layer	A layer of processing elements that receives the input to a neural net.
Kohonen Net	A neural net architecture whose processing elements compete with each other for the "right" to respond to an input pattern.
Neural Network	A system modeled after the neurons (nerve cells) in a biological nervous system. A neural network is designed as an interconnected system of processing elements, each with a limited number of inputs and outputs. Rather than being programmed, these systems learn to recognize patterns.
Output Layer	The layer of processing elements which produce a neural net's output.
	For More Info on Neural Networks

Object Oriented Development

Inheritance	The process where the properities of a superior object class are pushed upon a subordinate object class.
Object	A software structure which represents an identifiable item that has a well-defined role in a problem domain.
Object Oriented	An adjective applied to any system or language that supports the use of objects.
	For More Info on Object Oriented Development

OPS Programming Language

Action	In a forward-chaining production system, the right-hand side of a rule consisting of a secquence of actions.
Agenda	A control mechanism the handles a priority queue of tasks.
Antecedent	The statement of conditions necessary for coming to a conclusion. In a production system, this is the left-hand side of the rule.
Attribute	A property associated with an object.
Backtracking	A control method used to search backwards for solutions.
Backward-Chaining	A process used to find the solution by searching backwards from the solution towards the initial conditions thus verifying the specified goal.
Backus-Naur Form (BNF)	A formal language used to define context-free grammars where a formal grammer consists of a set of rules with a left and right side separated by the symbol '::='. The left hand side is a nonterminal symbol and the right-hand side is a sequence of nonterminal symbols.
Belief	A statement that is not known or assumed to be true.
Binding	The process of assigning a variable a value.
Bound	A variable that has been assigned a value in the binding process.
Condition Element	The left side of a rule that can be expressed as a pattern which can be matched against facts.
Control Strategy	The process for choosing the next action when there are many alternatives steps.
Data Memory	The global database used in a production system.
Demon	A procedure that is executed whenever a particular predicate about a database becomes true.
Execute	Do the steps specified in a procedure or the actions in a rule.
Forward-chaining	A process used to find the solution by starting with an assumption and working toward a final goal.
Frame	A formal method of representing information about a single idea or concept in terms of properties where the information is stored in slots.
Goal	The solution that the program is trying to reach.
Goal Directed	Same as backward chaining.
Learning	A change to a system that alters it's future performance and is usually associated with changes to rules.
Left Side	Specifies the antecedents that must be satisfied if the rule on the right-side is to be executed.
List	A series of recursively defined objects.
Match	Comparing the left side with data values in memory to find the ways in which rules can be satisfied.
Object	An entity in a programming system that is used to represent a piece of information or knowledge.
Procedure	Set of instructions for performing a task.
Production	Another name for rules.
Property	The features and characteristics of an object and the values are called attributes.
Right side	A series of actions taken in the specified sequence when a rule is fired.
Rule	Represents the relationship between objects and actions.
Scheme	Same as Frame.
Task	Another name for context or goal.
Variable	A term that can assume any value from a set of values.
	For More Info on the OPS Programming Language

Optical Character Recognition

Character Recognition	The process of applying pattern-matching methods to character shapes that have been read into a computer to determine the character that the shapes represent.
	For More Info on Optical Character Recognition

AI Info Pages

AI Languages ------------------------------------------------->		C++
Blackboard Technology	Client/Server	Dylan
Creative Thinking	Data Mining/Warehousing	Forth
Distributed Computing	Expert Systems	Lisp
Fuzzy Logic	General AI Sites	Logo
Genetic Algorithms	Help Desk	OPS
Intelligent Agents	Intelligent Applications	Prolog
Internet	Logic Programming	Scheme
Machine Learning	Modeling and Simulation	Smalltalk
Multimedia	Natural Language Processing
Neural Networks	Object Oriented Development
Optical Character Recognition	Robotics
Speech Recognition	Virtual Reality