{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:40:51Z","timestamp":1760136051141,"version":"build-2065373602"},"reference-count":39,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2022,1,16]],"date-time":"2022-01-16T00:00:00Z","timestamp":1642291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>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\u2019s 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\u2019 features and the model\u2019s learnt parameters, (2) the mathematical relationship between the images\u2019 features of a separate test dataset and a trained model\u2019s learnt parameters, and (3) the mathematical relationship between the difference of training and testing images\u2019 features and the model\u2019s 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\u2019s learnt weights by the ANOVA analysis.<\/jats:p>","DOI":"10.3390\/e24010132","type":"journal-article","created":{"date-parts":[[2022,1,16]],"date-time":"2022-01-16T20:44:00Z","timestamp":1642365840000},"page":"132","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Understanding Dilated Mathematical Relationship between Image Features and the Convolutional Neural Network\u2019s Learnt Parameters"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6904-8665","authenticated-orcid":false,"given":"Eyad","family":"Alsaghir","sequence":"first","affiliation":[{"name":"Institute for Digital Technologies, Loughborough University London, Queen Elizabeth Olympic Park, Here East, London E20 3BS, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6174-3383","authenticated-orcid":false,"given":"Xiyu","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute for Digital Technologies, Loughborough University London, Queen Elizabeth Olympic Park, Here East, London E20 3BS, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7535-141X","authenticated-orcid":false,"given":"Varuna","family":"De Silva","sequence":"additional","affiliation":[{"name":"Institute for Digital Technologies, Loughborough University London, Queen Elizabeth Olympic Park, Here East, London E20 3BS, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmet","family":"Kondoz","sequence":"additional","affiliation":[{"name":"Institute for Digital Technologies, Loughborough University London, Queen Elizabeth Olympic Park, Here East, London E20 3BS, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,1,16]]},"reference":[{"key":"ref_1","unstructured":"Kubilius, J., Schrimpf, M., Kar, K., Hong, H., Majaj, N.J., Rajalingham, R., Issa, E.B., Bashivan, P., Prescott-Roy, J., and Schmidt, K. (2019, January 10\u201312). Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada. Available online: https:\/\/dl.acm.org\/doi\/pdf\/10.5555\/3454287."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"4867","DOI":"10.1007\/s11042-018-6808-5","article-title":"A Comprehensive Overview of Feature Representation for Biometric Recognition","volume":"79","author":"Rida","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.patrec.2018.04.033","article-title":"Palmprint Recognition with an Efficient Data Driven Ensemble Classifier","volume":"126","author":"Rida","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1859","DOI":"10.1109\/ACCESS.2018.2886133","article-title":"Indoor Scene Understanding in 2.5\/3D for Autonomous Agents\u2014A Survey","volume":"7","author":"Naseer","year":"2019","journal-title":"IEEE Access"},{"key":"ref_5","unstructured":"Zolanvari, S.M.I., Ruano, S., Rana, A., Cummins, A., Da Silva, R.E., Rahbar, M., and Smolic, A. (2019, January 9\u201312). DublinCity: Annotated LiDAR Point Cloud and Its Applications. Proceedings of the 30th British Machine Vision Conference (BMVC 2019), Dublin, UK. Available online: https:\/\/bmvc2019.org\/wp-content\/uploads\/papers\/0644-paper.pdf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, J., Yuan, Y., Mei, K., and Fang, F. (2019, January 27\u201328). Lightweight and Accurate Recursive Fractal Network for Image Super-Resolution. Proceedings of the 2019 International Conference on Computer Vision Workshop, Seoul, Korea.","DOI":"10.1109\/ICCVW.2019.00474"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1088\/1742-6596\/1712\/1\/012015","article-title":"Image Captioning Using Deep Convolutional Neural Networks (CNNs)","volume":"1712","author":"Geetha","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hassaballah, M., and Awad, A.I. (2020). Object Detection with Convolutional Neural Networks. Deep Learning in Computer Vision Principles and Applications, CRC Press. [1st ed.].","DOI":"10.1201\/9781351003827"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"107687","DOI":"10.1016\/j.neuropsychologia.2020.107687","article-title":"Reaction Times Predict Dynamic Brain Representations Measured with MEG for Only Some Object Categorisation Tasks","volume":"151","author":"Contini","year":"2021","journal-title":"Neuropsychologia"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.future.2019.01.029","article-title":"Action Recognition Using Optimized Deep Autoencoder and CNN for Surveillance Data Streams of Non-Stationary Environments","volume":"96","author":"Ullah","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/BF02478112","article-title":"The Linear Theory of Neuron Networks: The Static Problem","volume":"4","author":"Pitts","year":"1942","journal-title":"Bull. Math. Biophys."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3599","DOI":"10.1109\/TGRS.2018.2886022","article-title":"A CNN with Multiscale Convolution and Diversified Metric for Hyperspectral Image Classification","volume":"57","author":"Gong","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1148\/radiol.2017171154","article-title":"Improving Arterial Spin Labeling by Using Deep Learning","volume":"287","author":"Kim","year":"2018","journal-title":"Radiology"},{"key":"ref_14","unstructured":"Rida, I., Al-Maadeed, N., Al-Maadeed, S., and Bakshi, S. (2016, January 17\u201321). Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI 2016), Athens, Greece."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/978-3-319-64816-3_4","article-title":"Social Planning for Trusted Autonomy","volume":"Volume 117","author":"Abbass","year":"2018","journal-title":"Foundations of Trusted Autonomy: An Introduction"},{"key":"ref_16","unstructured":"Sch\u00f6lkopf, B. (2019). Causality for Machine Learning. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-030-74009-2_5","article-title":"Increasing the Understandability and Explainability of Machine Learning and Artificial Intelligence Solutions: A Design Thinking Approach","volume":"Volume 1378","author":"Ahram","year":"2021","journal-title":"Human Interaction, Emerging Technologies and Future Applications IV"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Shi, X., De-Silva, V., Aslan, Y., Ekmekcioglu, E., and Kondoz, A. (2022). Evaluating the Learning Procedure of CNNs through a Sequence of Prognostic Tests Utilising Information Theoretical Measures. Entropy, 24.","DOI":"10.3390\/e24010067"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","unstructured":"Hutter, F., Hoos, H., and Leyton-Brown, K. (2014, January 21\u201326). An Efficient Approach for Assessing Hyperparameter Importance. Proceedings of the 31st International Conference on Machine Learning (ICML 2014), Beijing, China. Available online: http:\/\/proceedings.mlr.press\/v32\/hutter14.pdf."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Flusser, J., Suk, T., and Zitov\u00e1, B. (2017). 2D and 3D Image Analysis by Moments, John Wiley & Sons. [1st ed.].","DOI":"10.1002\/9781119039402"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kim, H., Nam, H., Jung, W., and Lee, J. (2017, January 24\u201325). Performance Analysis of CNN Frameworks for GPUs. Proceedings of the 2017 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Santa Rosa, CA, USA.","DOI":"10.1109\/ISPASS.2017.7975270"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kwasigroch, A., Miko\u0142ajczyk, A., and Grochowski, M. (2017, January 28\u201331). Deep Neural Networks Approach to Skin Lesions Classification\u2014A Comparative Analysis. Proceedings of the 22nd International Conference on Methods and Models in Automation and Robotics (MMAR), Miedzyzdroje, Poland.","DOI":"10.1109\/MMAR.2017.8046978"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Poojary, R., and Pai, A. (2019, January 19\u201321). Comparative Study of Model Optimization Techniques in Fine-Tuned CNN Models. Proceedings of the 2019 International Conference on Electrical and Computing Technologies and Applications (ICECTA), Ras Al Khaimah, United Arab Emirates.","DOI":"10.1109\/ICECTA48151.2019.8959681"},{"key":"ref_25","unstructured":"Dawani, J. (2020). Hands-On Mathematics for Deep Learning, Packt Publishing."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hegde, K., Yu, J., Agrawal, R., Yan, M., Pellauer, M., and Fletcher, C.W. (2018, January 1\u20136). UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition. Proceedings of the 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), Los Angeles, CA, USA.","DOI":"10.1109\/ISCA.2018.00062"},{"key":"ref_27","unstructured":"Han, S., Pool, J., Tran, J., and Dally, W.J. (2015, January 7\u201312). Learning Both Weights and Connections for Efficient Neural Networks. Proceedings of Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_28","unstructured":"Russell, S.J., and Norvig, P. (2020). Artificial Intelligence\u2014A Modern Approach, Pearsons. [4th ed.]."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TEVC.2019.2916183","article-title":"Evolving Deep Convolutional Neural Networks for Image Classification","volume":"24","author":"Sun","year":"2020","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C. (2018). Neural Networks and Deep Learning, Springer.","DOI":"10.1007\/978-3-319-94463-0"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Hassanien, A.E., and Oliva, D.A. (2018). Advances in Soft Computing and Machine Learning in Image Processing, Springer. [1st ed.].","DOI":"10.1007\/978-3-319-63754-9"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"8065396","DOI":"10.1155\/2020\/8065396","article-title":"Combining 3D-CNN and Squeeze-and-Excitation Networks for Remote Sensing Sea Ice Image Classification","volume":"2020","author":"Han","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"102705","DOI":"10.1016\/j.jvcir.2019.102705","article-title":"Research on Image Feature Extraction and Retrieval Algorithms Based on Convolutional Neural Network","volume":"69","author":"Peng","year":"2020","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_34","unstructured":"Kaggle (2020, April 01). Dogs vs. Cats. Kaggle, 2013. Available online: https:\/\/www.kaggle.com\/c\/dogs-vs-cats\/data."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/MMUL.2012.26","article-title":"Collecting Large, Richly Annotated Facial Expression Databases from Movies","volume":"19","author":"Dhall","year":"2012","journal-title":"IEEE MultiMedia"},{"key":"ref_36","unstructured":"Roy, P., Bhattacharya, S., and Ghosh, S. (2021, January 18). Natural Images. Kaggle, 2018. Available online: https:\/\/www.kaggle.com\/prasunroy\/natural-images."},{"key":"ref_37","unstructured":"Alsaghir, E. (2022, January 10). FW-Mathematical-Relationship. Available online: https:\/\/github.com\/eydoouk\/FW-mathematical-Relationship."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Paolella, M.S. (2018). Fixed Effects ANOVA Models. Linear Models and Time-Series Analysis: Regression, ANOVA, ARMA and GARCH, John Wiley & Sons Ltd.","DOI":"10.1002\/9781119432036"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Neapolitan, R.E., and Jiang, X. (2018). Learning Deterministic Models. Artificial Intelligence: With an Introduction to Machine Learning, CRC Press. [2nd ed.].","DOI":"10.1201\/b22400"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/1\/132\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:02:14Z","timestamp":1760133734000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/1\/132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,16]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["e24010132"],"URL":"https:\/\/doi.org\/10.3390\/e24010132","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2022,1,16]]}}}