Liu, ShuangrongOh, Sung-KwunPedrycz, WitoldYang, BoWang, LinPeng, Zhen2025-04-182025-04-182024Liu, S., Oh, S. K., Pedrycz, W., Yang, B., Wang, L., & Peng, Z. (2024). SCINN: Semantic Concept-Based Inference Neural Networks With Explainable and Deep Fuzzy Structure. IEEE Transactions on Fuzzy Systems.1063-67061941-0034http://dx.doi.org/10.1109/TFUZZ.2024.3398719https://hdl.handle.net/20.500.12713/7053In this study, a novel semantic concept-based inference neural network (SCINN) is proposed to develop a design methodology for the explainable deep neuro-fuzzy models and improve their generalization performance in high-dimensional problems. Traditional neuro-fuzzy models exhibit outstanding interpretability in the problems of lower dimensionality. However, when faced with high-dimensional scenarios, the long rule and rule explosion problems damage their interpretability and result in poor generalization performance, even making them unusable. Although deep neuro-fuzzy models show enhanced performance in handling high-dimensional problems compared to traditional counterparts, they often come at the expense of interpretability. To establish a neuro-fuzzy model that can address high-dimensional problems while preserving the interpretability, the SCINN is proposed with the aid of the concept-based measure generation paradigm (CMGP) and the multi-view information augmentation strategy (MIAS). The CMGP is designed to adaptively define the membership functions (MFs) that correspond to the human-understandable concepts based on the given data; the defined MFs contribute to the construction of the explainable fuzzy rule that can directly process high-dimensional data. The MIAS is structured to develop a unified paradigm for implementing consequence functions in the fuzzy rules, which enhances the approximation ability of the SCINN. The performance of SCINN is evaluated on various image datasets against different competitors, including neuro-fuzzy-based approaches and deep structure-based neural networks. A real-world application is adopted to evaluate its effectiveness. The experimental results show that SCINN outperforms the compared neuro-fuzzy models and is comparable to the deep structure-based neural networks.eninfo:eu-repo/semantics/closedAccessFuzzy Inference FrameworkGenerative Adversarial Network (GAN)InterpretabilityMultiviewInformation AugmentationSemantic Concept-Based InferenceArticle32741334147WOS:0012635987000162-s2.0-85192777364Q110.1109/TFUZZ.2024.3398719Q1