Next Article in Journal
Equisum Partitions of Sets of Positive Integers
Previous Article in Journal
Distributed Balanced Partitioning via Linear Embedding
Previous Article in Special Issue
Distributed Centrality Analysis of Social Network Data Using MapReduce
Article Menu

Export Article

Open AccessArticle

Idea of Using Blockchain Technique for Choosing the Best Configuration of Weights in Neural Networks

Institute of Mathematics, Silesian University of Technology, Kaszubska 23, 44-100 Gliwice, Poland
*
Author to whom correspondence should be addressed.
Algorithms 2019, 12(8), 163; https://doi.org/10.3390/a12080163
Received: 4 July 2019 / Revised: 1 August 2019 / Accepted: 6 August 2019 / Published: 10 August 2019
(This article belongs to the Special Issue Algorithms for Pattern Recognition)
  |  
PDF [360 KB, uploaded 16 August 2019]
  |  

Abstract

The blockchain technique is becoming more and more popular due to its advantages such as stability and dispersed nature. This is an idea based on blockchain activity paradigms. Another important field is machine learning, which is increasingly used in practice. Unfortunately, the training or overtraining artificial neural networks is very time-consuming and requires high computing power. In this paper, we proposed using a blockchain technique to train neural networks. This type of activity is important due to the possible search for initial weights in the network, which affect faster training, due to gradient decrease. We performed the tests with much heavier calculations to indicate that such an action is possible. However, this type of solution can also be used for less demanding calculations, i.e., only a few iterations of training and finding a better configuration of initial weights. View Full-Text
Keywords: algorithms; blockchain; machine learning algorithms; blockchain; machine learning
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Winnicka, A.; Kęsik, K. Idea of Using Blockchain Technique for Choosing the Best Configuration of Weights in Neural Networks. Algorithms 2019, 12, 163.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top