Convolutional operations have been one of the mechanisms of functional processing of neural networks, especially present as a part of convolutional neural networks. Fuzzy convolution (composition operation) has been widely explored. within the framework of fuzzy relational equations, its integration into computational architectures such as neural networks remains underexplored. This study introduces a framework that formally extends conventional convolution into the domain of fuzzy set theory through the development of fuzzy convolution operations. We formulate and solve an optimization problem aimed at fine-tuning fuzzy convolution kernels using established fuzzy relational structures, thereby enhancing the interpretability of neural processing. Several t-norms and t-conorms that implement convolution operators are examined within the framework of s-t and t-s convolutions (compositions) of fuzzy relations. A detailed derivation of the optimization schemes is presented. Several experiments on images are conducted, demonstrating that even with a data size reduction of up to 75%, the method can still effectively reconstruct images by optimizing the parameters of the relational architecture.
Al-HmouzR.PedryczW.AmmariA. C.Al-HmouzA. (2022). A data variability index: Quantifying complexity of models and analyzing adversarial data. International Journal of Intelligent Systems, 37, 8412–8435. https://doi.org/10.1002/int.22947
3.
BazinA. (2023). A triadic generalisation of the boolean concept lattice. In DürrschnabelD.López RodríguezD. (Eds.), Formal concept analysis, lecture notes in computer science (Vol. 13934, pp. 108–123). Springer. [Online]. Available: https://doi.org/10.1007/978-3-031-35949-1_7
4.
ChenL.WuM.ZhouM.LiuZ.SheJ.HirotaK. (2020). Dynamic emotion understanding in human–robot interaction based on two-layer fuzzy SVR-TS model. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50(2), 490–501. https://doi.org/10.1109/TSMC.2017.2756447
5.
De BaetsB.KerreE. (1994). Fuzzy relations and applications. In Advances in electronics and electron physics* (Vol. 89, pp. 255–324). Academic Press.
6.
Di NolaA.PedryczW.SessaS.SanchezE. (1991). Fuzzy relation equations theory as a basis of fuzzy modelling: An overview. Fuzzy Sets and Systems, 40(3), 415–429. https://doi.org/10.1016/0165-0114(91)90170-U
7.
Di NolaA.SessaS.PedryczW.SanchezE. (1989). Fuzzy relation equations and their applications to knowledge engineering. Kluwer Academic Publishers.
8.
GhodousianA.ChopannavazM. S.PedryczW. (2025). On the resolution and linear optimization problems subject to a system of bipolar fuzzy relational equalities defined with continuous Archimedean t-norms arXiv preprint, arXiv:2503.05874.
9.
HuangH.OhS.-K.FuZ.WuC.-K.PedryczW.KimJ.-Y. (2024). FSCNN: Fuzzy channel filter-based separable convolution neural networks for medical imaging recognition. IEEE Transactions on Fuzzy Systems, 32(10), 5449–5461. https://doi.org/10.1109/TFUZZ.2024.3450000
10.
KingmaD. P.BaJ. (2014). ADAM: A method for stochastic optimization. Proc. 3rd Int. Conf. Learn, Representations (ICLR), San Diego, CA.
LiM.ZhangX.JiangH.LiuJ. (2025). Some novel fuzzy logic operators with applications in fuzzy neural networks. Information Science, 121897. https://doi.org/10.1016/j.ins.2025.121897
13.
LoboD.López-MarchanteV.MedinaJ. (2023). Reducing fuzzy relation equations via concept lattices. Fuzzy Sets and Systems, 463, 108465. https://doi.org/10.1016/j.fss.2022.12.021
14.
MaC.ZhangL.PedryczW.LuW. (2022). The long-term prediction of time series: A granular computing-based design approach. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(10), 6326–6338. https://doi.org/10.1109/TSMC.2022.3144395
15.
NobuharaH.PedryczW.HirotaK. (2000). Fast solving method of fuzzy relational equation and its application to lossy image compression. IEEE Transactions on Fuzzy Systems, 8, 325–334. https://doi.org/10.1109/91.855920
SessaS.MartinoF. D. (2022). Special issue: Fuzzy relation equations: Trends and applications. Symmetry, 14(10), 4516.
18.
StamouG. B.TzafestasS. G. (1999). Fuzzy relation equations and fuzzy inference systems: An inside approach. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 29(6), 694–702. https://doi.org/10.1109/3477.809025
19.
ValenkovaD.LyanovaA.SinitcaA.SarkarR.KaplunD. (2025). A fuzzy rank-based ensemble of CNN models for MRI segmentation. Biomedical Signal Processing and Control, 102, 107342. https://doi.org/10.1016/j.bspc.2024.107342
20.
WangC.LvX.ShaoM.QianY.ZhangY. (2023). A novel fuzzy hierarchical fusion attention convolution neural network for medical image super-resolution reconstruction. Information Science, 622, 424–436. https://doi.org/10.1016/j.ins.2022.11.140
WuM.SuW.ChenL.PedryczW.HirotaK. (2022). Two-stage fuzzy fusion based-convolution neural network for dynamic emotion recognition. IEEE Transactions on Affective Computing, 13(2), 805–817. https://doi.org/10.1109/TAFFC.2020.2966440
23.
XuJ.LiK.LiZ.ChongQ.XingH.XingQ.NiM. (2024). Fuzzy graph convolutional network for hyperspectral image classification. Engineering Applications of Artificial Intelligence, 127, 107280. https://doi.org/10.1016/j.engappai.2023.107280
24.
YuB.XieH.XuZ. (2023). PN-GCN: Positive-negative graph convolution neural network in information systems for classification. Information Science, 632, 411–423. https://doi.org/10.1016/j.ins.2023.03.013
