Interpretation of deep non-linear factorization for autism
Autism, a neurodevelopmental disorder, presents significant challenges for diagnosis and classification. Despite the widespread use of neural networks in autism classification, the interpretability of their models remains a crucial issue. This study aims to address this concern by investigating the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1199113/full |
| _version_ | 1797797699598155776 |
|---|---|
| author | Boran Chen Bo Yin Hengjin Ke Hengjin Ke |
| author_facet | Boran Chen Bo Yin Hengjin Ke Hengjin Ke |
| author_sort | Boran Chen |
| collection | DOAJ |
| description | Autism, a neurodevelopmental disorder, presents significant challenges for diagnosis and classification. Despite the widespread use of neural networks in autism classification, the interpretability of their models remains a crucial issue. This study aims to address this concern by investigating the interpretability of neural networks in autism classification using the deep symbolic regression and brain network interpretative methods. Specifically, we analyze publicly available autism fMRI data using our previously developed Deep Factor Learning model on a Hibert Basis tensor (HB-DFL) method and extend the interpretative Deep Symbolic Regression method to identify dynamic features from factor matrices, construct brain networks from generated reference tensors, and facilitate the accurate diagnosis of abnormal brain network activity in autism patients by clinicians. Our experimental results show that our interpretative method effectively enhances the interpretability of neural networks and identifies crucial features for autism classification. |
| first_indexed | 2024-03-13T03:53:20Z |
| format | Article |
| id | doaj.art-e62787f70f664093aeda47c54f61907d |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-03-13T03:53:20Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-e62787f70f664093aeda47c54f61907d2023-06-22T09:41:50ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402023-06-011410.3389/fpsyt.2023.11991131199113Interpretation of deep non-linear factorization for autismBoran Chen0Bo Yin1Hengjin Ke2Hengjin Ke3Computer School (Huangshi Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence), Hubei Polytechnic University, Huangshi, ChinaComputer School (Huangshi Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence), Hubei Polytechnic University, Huangshi, ChinaComputer School (Huangshi Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence), Hubei Polytechnic University, Huangshi, ChinaComputer School, Wuhan University, Wuhan, ChinaAutism, a neurodevelopmental disorder, presents significant challenges for diagnosis and classification. Despite the widespread use of neural networks in autism classification, the interpretability of their models remains a crucial issue. This study aims to address this concern by investigating the interpretability of neural networks in autism classification using the deep symbolic regression and brain network interpretative methods. Specifically, we analyze publicly available autism fMRI data using our previously developed Deep Factor Learning model on a Hibert Basis tensor (HB-DFL) method and extend the interpretative Deep Symbolic Regression method to identify dynamic features from factor matrices, construct brain networks from generated reference tensors, and facilitate the accurate diagnosis of abnormal brain network activity in autism patients by clinicians. Our experimental results show that our interpretative method effectively enhances the interpretability of neural networks and identifies crucial features for autism classification.https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1199113/fullinterpretationautismfMRIdeep symbolic regressionbrain networkfactorization |
| spellingShingle | Boran Chen Bo Yin Hengjin Ke Hengjin Ke Interpretation of deep non-linear factorization for autism Frontiers in Psychiatry interpretation autism fMRI deep symbolic regression brain network factorization |
| title | Interpretation of deep non-linear factorization for autism |
| title_full | Interpretation of deep non-linear factorization for autism |
| title_fullStr | Interpretation of deep non-linear factorization for autism |
| title_full_unstemmed | Interpretation of deep non-linear factorization for autism |
| title_short | Interpretation of deep non-linear factorization for autism |
| title_sort | interpretation of deep non linear factorization for autism |
| topic | interpretation autism fMRI deep symbolic regression brain network factorization |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1199113/full |
| work_keys_str_mv | AT boranchen interpretationofdeepnonlinearfactorizationforautism AT boyin interpretationofdeepnonlinearfactorizationforautism AT hengjinke interpretationofdeepnonlinearfactorizationforautism AT hengjinke interpretationofdeepnonlinearfactorizationforautism |