An embedded deep fuzzy association model for learning and explanation
This paper explores the complementary benefits of embedding a deep learning model as a fully data-driven fuzzy implication operator of a five-layer neuro-fuzzy system for learning and explanations for the predictions of both steady-state and dynamically changing data. In traditional Mandani-type neu...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/164597 |
| _version_ | 1826109463037214720 |
|---|---|
| author | Xie, Chen Rajan, Deepu Prasad, Dilip K. Quek, Chai |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Xie, Chen Rajan, Deepu Prasad, Dilip K. Quek, Chai |
| author_sort | Xie, Chen |
| collection | NTU |
| description | This paper explores the complementary benefits of embedding a deep learning model as a fully data-driven fuzzy implication operator of a five-layer neuro-fuzzy system for learning and explanations for the predictions of both steady-state and dynamically changing data. In traditional Mandani-type neuro-fuzzy systems, the entailment performed by the implication is realized using the fuzzy implication operator based on the fuzzy rules formed in the rule base during encoding and recall. Given the presence of a group of test data that are significantly different from the training data, the realization of entailments through the use of the implication operator based on the fuzzy rules formed in traditional neuro-fuzzy systems may not be adequate. This paper attempts to adopt a more direct approach by embedding a deep learning model in the neuro-fuzzy system to serve as a fuzzy implication operator, thereby allowing the data-driven learning of fuzzy implication using the deep structure to provide a close correspondence to the real-world entailment of data. In addition, embedding the neuro-fuzzy architecture within the deep learning model allows the comprehension of the learning and explanation of the reasoning of the deep network. The induced fuzzy association rules impart transparency to the deep learning based implication using a common set of semantic meanings, which are amenable to human interpretability. The effectiveness of the proposed model is evaluated on a continuously stirred tank reactor dataset and three financial stock prediction datasets. Experimental results showed that the proposed model outperformed other state-of-the-art techniques based on the four datasets, which contain high levels of uncertainties. |
| first_indexed | 2024-10-01T02:18:38Z |
| format | Journal Article |
| id | ntu-10356/164597 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:18:38Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1645972023-02-06T05:33:20Z An embedded deep fuzzy association model for learning and explanation Xie, Chen Rajan, Deepu Prasad, Dilip K. Quek, Chai School of Computer Science and Engineering Engineering::Computer science and engineering Neuro-Fuzzy Systems Deep Learning Network This paper explores the complementary benefits of embedding a deep learning model as a fully data-driven fuzzy implication operator of a five-layer neuro-fuzzy system for learning and explanations for the predictions of both steady-state and dynamically changing data. In traditional Mandani-type neuro-fuzzy systems, the entailment performed by the implication is realized using the fuzzy implication operator based on the fuzzy rules formed in the rule base during encoding and recall. Given the presence of a group of test data that are significantly different from the training data, the realization of entailments through the use of the implication operator based on the fuzzy rules formed in traditional neuro-fuzzy systems may not be adequate. This paper attempts to adopt a more direct approach by embedding a deep learning model in the neuro-fuzzy system to serve as a fuzzy implication operator, thereby allowing the data-driven learning of fuzzy implication using the deep structure to provide a close correspondence to the real-world entailment of data. In addition, embedding the neuro-fuzzy architecture within the deep learning model allows the comprehension of the learning and explanation of the reasoning of the deep network. The induced fuzzy association rules impart transparency to the deep learning based implication using a common set of semantic meanings, which are amenable to human interpretability. The effectiveness of the proposed model is evaluated on a continuously stirred tank reactor dataset and three financial stock prediction datasets. Experimental results showed that the proposed model outperformed other state-of-the-art techniques based on the four datasets, which contain high levels of uncertainties. 2023-02-06T05:33:20Z 2023-02-06T05:33:20Z 2022 Journal Article Xie, C., Rajan, D., Prasad, D. K. & Quek, C. (2022). An embedded deep fuzzy association model for learning and explanation. Applied Soft Computing, 131, 109738-. https://dx.doi.org/10.1016/j.asoc.2022.109738 1568-4946 https://hdl.handle.net/10356/164597 10.1016/j.asoc.2022.109738 2-s2.0-85141535204 131 109738 en Applied Soft Computing © 2022 Published by Elsevier B.V. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Neuro-Fuzzy Systems Deep Learning Network Xie, Chen Rajan, Deepu Prasad, Dilip K. Quek, Chai An embedded deep fuzzy association model for learning and explanation |
| title | An embedded deep fuzzy association model for learning and explanation |
| title_full | An embedded deep fuzzy association model for learning and explanation |
| title_fullStr | An embedded deep fuzzy association model for learning and explanation |
| title_full_unstemmed | An embedded deep fuzzy association model for learning and explanation |
| title_short | An embedded deep fuzzy association model for learning and explanation |
| title_sort | embedded deep fuzzy association model for learning and explanation |
| topic | Engineering::Computer science and engineering Neuro-Fuzzy Systems Deep Learning Network |
| url | https://hdl.handle.net/10356/164597 |
| work_keys_str_mv | AT xiechen anembeddeddeepfuzzyassociationmodelforlearningandexplanation AT rajandeepu anembeddeddeepfuzzyassociationmodelforlearningandexplanation AT prasaddilipk anembeddeddeepfuzzyassociationmodelforlearningandexplanation AT quekchai anembeddeddeepfuzzyassociationmodelforlearningandexplanation AT xiechen embeddeddeepfuzzyassociationmodelforlearningandexplanation AT rajandeepu embeddeddeepfuzzyassociationmodelforlearningandexplanation AT prasaddilipk embeddeddeepfuzzyassociationmodelforlearningandexplanation AT quekchai embeddeddeepfuzzyassociationmodelforlearningandexplanation |