Weight Exchange in Distributed Learning

Loading...
Thumbnail Image

Date

2016

Authors

Dorner, Julian
Favrichon, Samuel
Öğrenci, Arif Selçuk

Journal Title

Journal ISSN

Volume Title

Publisher

IEEE

Open Access Color

OpenAIRE Downloads

OpenAIRE Views

Research Projects

Organizational Units

Journal Issue

Abstract

Neural networks may allow different organisations to extract knowledge from the data they collect about a similar problem domain. Moreover learning algorithms usually benefit from being able to use more training instances. But the parties owning the data are not always keen on sharing it. We propose a way to implement distributed learning to improve the performance of neural networks without sharing the actual data among different organisations. This paper deals with the alternative methods of determining the weight exchange mechanisms among nodes. The key is to implement the epochs of learning separately at each node and then to select the best weight set among the different neural networks and to publish them to each node. The results show that an increase in performance can be achieved by deploying simple methods for weight exchange.

Description

Keywords

Turkish CoHE Thesis Center URL

Fields of Science

Citation

0

WoS Q

N/A

Scopus Q

N/A

Source

Volume

Issue

Start Page

3081

End Page

3084