Application of XML for neural network exchange

Authors:
Denis V. Rubtsov;Sergei V. Butakov
Affiliations:
Department of Mathematics, Altai State University, 61a Lenina Street, Barnaul 656099, Russia;Altai State Technical University, 49-5 Lenina Street, Barnaul 656099, Russia
Venue:
Computer Standards & Interfaces - XML Diffusion: Transfer and differentiation
Year:
2002

Citing 4
Cited 2

Neurocomputing

Neurocomputing
Simulation of artificial neural networks

Systems Analysis Modelling Simulation
EpsiloNN—a tool for the abstract specification and parallel simulation of neural networks

Systems Analysis Modelling Simulation - Special issue: simulation of artificial neural networks
A Formal Model for Definition and Simulation of Generic Neural Networks

Neural Processing Letters

Universal fuzzy system representation with XML

Computer Standards & Interfaces
XML based architectures for documents comparison, categorisation, and scrutinisation

International Journal of Data Analysis Techniques and Strategies

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article introduces a framework for the interchange of trained neural network models. An XML-based language (Neural Network Markup Language) for the neural network model description is offered. It allows to write down all the components of neural network model which are necessary for its reproduction. We propose to use XML notation for the full description of neural models, including data dictionary, properties of training sample, preprocessing methods, details of network structure and parameters and methods for network output interpretation.