Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron
A conventional scheme to operate neural networks until recently has been assigning the architecture of a neural network and its subsequent training. However, the latest research in this field has revealed that the neural networks that had been set and configured in this way exhibited considerable re...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
PC Technology Center
2020-04-01
|
Series: | Eastern-European Journal of Enterprise Technologies |
Subjects: | |
Online Access: | http://journals.uran.ua/eejet/article/view/200819 |
id |
doaj-3a9e4c038c4040a39537c949d1f9859c |
---|---|
record_format |
Article |
spelling |
doaj-3a9e4c038c4040a39537c949d1f9859c2020-11-25T02:04:38ZengPC Technology CenterEastern-European Journal of Enterprise Technologies1729-37741729-40612020-04-0129 (104)61310.15587/1729-4061.2020.200819200819Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptronOleg Galchonkov0Alexander Nevrev1Maria Glava2Mykola Babych3Odessa National Polytechnic University Shevchenka ave., 1, Odessa, Ukraine, 65044Odessa National Polytechnic University Shevchenka ave., 1, Odessa, Ukraine, 65044Odessa National Polytechnic University Shevchenka ave., 1, Odessa, Ukraine, 65044Odessa National Polytechnic University Shevchenka ave., 1, Odessa, Ukraine, 65044A conventional scheme to operate neural networks until recently has been assigning the architecture of a neural network and its subsequent training. However, the latest research in this field has revealed that the neural networks that had been set and configured in this way exhibited considerable redundancy. Therefore, the additional operation was to eliminate this redundancy by pruning the connections in the architecture of a neural network. Among the many approaches to eliminating redundancy, the most promising one is the combined application of several methods when their cumulative effect exceeds the sum of effects from employing each of them separately. We have performed an experimental study into the effectiveness of the combined application of iterative pruning and pre-processing (pre-distortions) of input data for the task of recognizing handwritten digits with the help of a multilayer perceptron. It has been shown that the use of input data pre-processing regularizes the procedure of training a neural network, thereby preventing its retraining. The combined application of the iterative pruning and pre-processing of input data has made it possible to obtain a smaller error in the recognition of handwritten digits, 1.22 %, compared to when using the thinning only (the error decreased from 1.89 % to 1.81 %) and when employing the predistortions only (the error decreased from 1.89 % to 1.52 %). In addition, the regularization involving pre-distortions makes it possible to receive a monotonously increasing number of disconnected connections while maintaining the error at 1.45 %. The resulting learning curves for the same task but corresponding to the onset of training under different initial conditions acquire different values both in the learning process and at the end of the training. This shows the multi-extreme character of the quality function – the accuracy of recognition. The practical implication of the study is our proposal to run the multiple training of a neural network in order to choose the best resulthttp://journals.uran.ua/eejet/article/view/200819multilayer perceptronneural networkpruningregularizationlearning curveweight coefficients |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Oleg Galchonkov Alexander Nevrev Maria Glava Mykola Babych |
spellingShingle |
Oleg Galchonkov Alexander Nevrev Maria Glava Mykola Babych Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron Eastern-European Journal of Enterprise Technologies multilayer perceptron neural network pruning regularization learning curve weight coefficients |
author_facet |
Oleg Galchonkov Alexander Nevrev Maria Glava Mykola Babych |
author_sort |
Oleg Galchonkov |
title |
Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron |
title_short |
Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron |
title_full |
Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron |
title_fullStr |
Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron |
title_full_unstemmed |
Exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron |
title_sort |
exploring the efficiency of the combined application of connection pruning and source data preprocessing when training a multilayer perceptron |
publisher |
PC Technology Center |
series |
Eastern-European Journal of Enterprise Technologies |
issn |
1729-3774 1729-4061 |
publishDate |
2020-04-01 |
description |
A conventional scheme to operate neural networks until recently has been assigning the architecture of a neural network and its subsequent training. However, the latest research in this field has revealed that the neural networks that had been set and configured in this way exhibited considerable redundancy. Therefore, the additional operation was to eliminate this redundancy by pruning the connections in the architecture of a neural network. Among the many approaches to eliminating redundancy, the most promising one is the combined application of several methods when their cumulative effect exceeds the sum of effects from employing each of them separately. We have performed an experimental study into the effectiveness of the combined application of iterative pruning and pre-processing (pre-distortions) of input data for the task of recognizing handwritten digits with the help of a multilayer perceptron. It has been shown that the use of input data pre-processing regularizes the procedure of training a neural network, thereby preventing its retraining. The combined application of the iterative pruning and pre-processing of input data has made it possible to obtain a smaller error in the recognition of handwritten digits, 1.22 %, compared to when using the thinning only (the error decreased from 1.89 % to 1.81 %) and when employing the predistortions only (the error decreased from 1.89 % to 1.52 %). In addition, the regularization involving pre-distortions makes it possible to receive a monotonously increasing number of disconnected connections while maintaining the error at 1.45 %. The resulting learning curves for the same task but corresponding to the onset of training under different initial conditions acquire different values both in the learning process and at the end of the training. This shows the multi-extreme character of the quality function – the accuracy of recognition. The practical implication of the study is our proposal to run the multiple training of a neural network in order to choose the best result |
topic |
multilayer perceptron neural network pruning regularization learning curve weight coefficients |
url |
http://journals.uran.ua/eejet/article/view/200819 |
work_keys_str_mv |
AT oleggalchonkov exploringtheefficiencyofthecombinedapplicationofconnectionpruningandsourcedatapreprocessingwhentrainingamultilayerperceptron AT alexandernevrev exploringtheefficiencyofthecombinedapplicationofconnectionpruningandsourcedatapreprocessingwhentrainingamultilayerperceptron AT mariaglava exploringtheefficiencyofthecombinedapplicationofconnectionpruningandsourcedatapreprocessingwhentrainingamultilayerperceptron AT mykolababych exploringtheefficiencyofthecombinedapplicationofconnectionpruningandsourcedatapreprocessingwhentrainingamultilayerperceptron |
_version_ |
1724942011202535424 |