A Framework for Ontology Based Management of Neural Network as a Service

A Framework for Ontology Based Management of Neural Network as a Service

Abstract

Neural networks proved extremely feasible for problems which are hard to solve by conventional computational algorithms due to excessive computational demand, as NP-hard problems, or even lack of a deterministic solution approach. In this paper we present a management framework for neural network objects based on ontology knowledge for the cloud-based neural network simulator N2Sky, which delivers neural network resources as a service on a world-wide basis. Core of this framework is the Neural Network Query Engine, N2Query, which allows users to specify their problem statements in form of natural language queries. It delivers a list of ranked N2Sky resources in return, providing solutions to these problems. The search algorithm applies a mapping process between a domain specific problem ontology and solution ontology.

Grafik Top
Authors
  • Schikuta, Erich
  • Magdy, Abdelkader
  • Mohamed, A. Baith
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Full Paper in Proceedings)
Event Title
23rd International Conference on Neural Information Processing (ICONIP 2016)
Divisions
Workflow Systems and Technology
Subjects
Webentwicklung, Webanwendungen
Kuenstliche Intelligenz
Angewandte Informatik
Event Location
Kyoto, Japan
Event Type
Conference
Event Dates
October 16 to 21, 2016
Date
October 2016
Export
Grafik Top