entropy-24-00132-v2.pdf (1.6 MB)
Download file

Understanding dilated mathematical relationship between image features and the convolutional neural network’s learnt parameters

Download (1.6 MB)
journal contribution
posted on 18.01.2022, 14:26 by Eyad AlsaghirEyad Alsaghir, Xiyu ShiXiyu Shi, Varuna De-SilvaVaruna De-Silva, Ahmet Kondoz
Deep learning, in general, was built on input data transformation and presentation, model training with parameter tuning, and recognition of new observations using the trained model. However, this came with a high computation cost due to the extensive input database and the length of time required in training. Despite the model learning its parameters from the transformed input data, no direct research has been conducted to investigate the mathematical relationship between the transformed information (i.e., features, excitation) and the model’s learnt parameters (i.e., weights). This research aims to explore a mathematical relationship between the input excitations and the weights of a trained convolutional neural network. The objective is to investigate three aspects of this assumed feature-weight relationship: (1) the mathematical relationship between the training input images’ features and the model’s learnt parameters, (2) the mathematical relationship between the images’ features of a separate test dataset and a trained model’s learnt parameters, and (3) the mathematical relationship between the difference of training and testing images’ features and the model’s learnt parameters with a separate test dataset. The paper empirically demonstrated the existence of this mathematical relationship between the test image features and the model’s learnt weights by the ANOVA analysis.

History

School

  • Loughborough University London

Published in

Entropy

Volume

24

Issue

1

Publisher

MDPI AG

Version

VoR (Version of Record)

Rights holder

© the Authors

Publisher statement

This is an Open Access Article. It is published by MDPI under the Creative Commons Attribution 4.0 Unported Licence (CC BY). Full details of this licence are available at: http://creativecommons.org/licenses/by/4.0/

Acceptance date

12/01/2022

Publication date

2022-01-16

Copyright date

2022

eISSN

1099-4300

Language

en

Depositor

Dr Xiyu Shi. Deposit date: 17 January 2022

Article number

132