Ontology Creation

Ontology Creation

Anjali Daisy
Copyright: © 2020 |Pages: 12
DOI: 10.4018/978-1-7998-1159-6.ch005
OnDemand:
(Individual Chapters)
Available
$33.75
List Price: $37.50
Current Special Offers
10% Discount:-$3.75
TOTAL SAVINGS: $3.75

Abstract

Neural networks are like the models of the brain and nervous system. It is highly parallel and processes information much more like the brain than a serial computer. It is very useful in learning information, using and executing very simple and complex behaviors, applications like powerful problem solvers and biological models. There are different types of neural networks like Biological, Feed Forward, Recurrent, and Elman. Biological Neural Networks require some biological data to predict information. In Feed Forward Networks, information flows in one way. In Recurrent Networks, information flows in multiple directions. Elman Networks feature Partial re-currency with a sense of time.
Chapter Preview
Top

Introduction

Neural networks are like the models of the brain and nervous system. It is highly parallel and process information much more like the brain than a serial computer. It is very much useful in learning information, using and executing very simple and complex behaviours, applications like powerful problem solvers and biological models. There are different types of neural networks like Biological, Feed Forward, Recurrent and Elman neural networks. Biological Neural Networks: It requires some biological data to predict information. Feed Forward Networks: Information flows in one way. Recurrent Networks: Information flows in multidirectional. Elman Networks: Partial re-currency with sense of time.

Ontology Creation

Ontology

Ontology is closely connected to Natural Language Processing (NLP) - a field of artificial intelligence, computer science and linguistics. As such, NLP is related to the area of human–computer interaction. Because of that the production of software tools to support ontology and Semantic web has accelerated. In AI, ontology is defined as domain knowledge representation that facilitates common understanding of that domain. It is a logical combination of a domain concepts and their relationship. It is a good way to represent knowledge graphically.

Figure 1.
978-1-7998-1159-6.ch005.f01

Methods to Create Ontology

There are some methods to create ontology. They are as follows,

  • •

    Define concepts, i.e., classes.

  • •

    Organize them somehow in taxonomy.

  • •

    Define relations among the classes.

  • •

    Define the attributes and which values they can take.

  • •

    Define instances, i.e., “real” elements in our domain.

  • •

    Create axioms and functions.

Top

Steps To Follow In Ontology Creation

Determine the Domain and the Scope or Purpose of Our Ontology

Basically, try to find an answer to questions such as:

  • •

    Which domain are we thinking of?

  • •

    What will we use the ontology for?

  • •

    Is it going to be just one, or will we need different sub ontologies to make it clearer?

  • •

    Who will use the ontology?

It is the hardest part to develop the ontology. It might be further clarified, but at least we need a good initial scope or purpose for our ontology. Formally, it is done using competency questions, which we think might prove useful once the ontology is started. Not the other way round. And remember, we can go through them as many times as needed. New questions will arise and former answers might change. Some other people prefer to make use scenarios of how/what for the ontology will be used.

Example: OASys (Ontology for Autonomous Systems) is ontology for the domain of autonomous systems, understanding as such systems capable of fulfilling a goal in an environment by adapting to changes to some extent (not to mention cognitive capabilities). We will try to use it to describe what such systems need to work as well as who and how they will be developed. Probably, we will need several sub ontologies(structure, behavior, agents), as the domain seems complex enough. The ontology is intended for autonomous systems developers and engineers.

Complete Chapter List

Search this Book:
Reset