{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T18:30:14Z","timestamp":1784745014626,"version":"3.55.0"},"reference-count":123,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Evolving Systems"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Interpretability in deep learning, particularly in convolutional neural networks (CNNs), remains a critical challenge due to the complexity of models obscuring decision-making processes. This study performs a rigorous comparative analysis of two key filter-level explanation strategies: removal-based and zeroing-based methods. The evaluation framework is grounded in fidelity, sparsity, robustness, and human interpretability. Extensive experiments were conducted using CNN architectures like ResNet-50 and VGG-16, across diverse medical imaging datasets, including brain tumors, prostatic hyperplasia, and breast cancer. The analysis reveals distinct behavioral patterns and practical implications for both strategies. Filter removal can sometimes mislead interpretations by overemphasizing or suppressing features, potentially altering model behavior. Conversely, zeroing-based methods better preserve structural fidelity, providing more stable and interpretable pathways for class-specific predictions. By leveraging activation visualizations and zeroing strategies, the study offers clearer insights into class predictions and decision processes. The work contributes a foundational understanding for integrating filter-based interpretability into practical AI development, especially for model debugging and deployment in clinical contexts. Overall, the findings advance understanding of CNN behavior and support the creation of trustworthy, human-aligned explanations essential in high-stakes decision-making environments such as healthcare.<\/jats:p>","DOI":"10.1007\/s12530-026-09840-y","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T06:40:14Z","timestamp":1781678414000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dissecting deep models: removal and zeroing-based explanation (RZE) techniques"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1530-3293","authenticated-orcid":false,"given":"Stanley","family":"Ziweritin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abirami","family":"Gunasekaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shamaila","family":"Iram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"9840_CR1","doi-asserted-by":"publisher","first-page":"130657","DOI":"10.1109\/ACCESS.2022.3228744","volume":"10","author":"S Abdullah","year":"2022","unstructured":"Abdullah S, Zamani M, Demosthenous A (2022) A compact CNN-Based speech enhancement with adaptive filter design using gabor function and region-aware convolution. IEEE Access 10:130657\u2013130671. https:\/\/ieeexplore.ieee.org\/document\/9982431","journal-title":"IEEE Access"},{"key":"9840_CR2","doi-asserted-by":"publisher","DOI":"10.1017\/S1748499524000058","author":"A Alex Jose","year":"2024","unstructured":"Alex Jose A, Macdonald A, Tzougas G, Streftaris G (2024) Interpretable zero-inflated neural network models for predicting admission counts. Annals Actuar Sci. https:\/\/doi.org\/10.1017\/S1748499524000058","journal-title":"Annals Actuar Sci"},{"issue":"2","key":"9840_CR3","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3390\/jimaging9020046","volume":"9","author":"K Alomar","year":"2023","unstructured":"Alomar K, Aysel H, I, Cai X (2023) Data augmentation in classification and segmentation: A survey and new strategies. MDPI: J imaging 9(2):46. https:\/\/doi.org\/10.3390\/jimaging9020046","journal-title":"MDPI: J imaging"},{"key":"9840_CR4","doi-asserted-by":"publisher","unstructured":"Alvarez-Melis, Jaakkola TS (2018) On the robustness of interpretability methods, presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden. https:\/\/doi.org\/10.48550\/arXiv.1806.08049","DOI":"10.48550\/arXiv.1806.08049"},{"key":"9840_CR5","doi-asserted-by":"publisher","first-page":"19475","DOI":"10.1038\/s41598-025-05136-4","volume":"15","author":"S Alzanin","year":"2025","unstructured":"Alzanin S (2025) Explainable artificial intelligence with temporal convolutional networks for adverse weather condition detection in driverless vehicles. Sci Rep 15:19475. https:\/\/doi.org\/10.1038\/s41598-025-05136-4","journal-title":"Sci Rep"},{"key":"9840_CR6","doi-asserted-by":"publisher","first-page":"58229","DOI":"10.1109\/ACCESS.2025.3555543","volume":"13","author":"S Amirian","year":"2025","unstructured":"Amirian S, Gao F, Littlefield N, Hill JH, Yates AJ, Plate J, Pantanowitz L, Rashidi H, Tafti AP (2025) State-of-the-art in responsible, explainable, and fair AI for medical analysis. IEEE Open Access J 13:58229\u201358263. https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=10942605","journal-title":"IEEE Open Access J"},{"key":"9840_CR8","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.inffus.2021.07.015","volume":"77","author":"CJ Anders","year":"2022","unstructured":"Anders CJ, Weber L, Neumann D, Samek W, Muller KR, Lapuschkin S (2022) Finding and removing clever hans: using explainable methods to debug and improve deep models. Inform fusion 77:261\u2013295. https:\/\/doi.org\/10.1016\/j.inffus.2021.07.015","journal-title":"Inform fusion"},{"key":"9840_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2025.102972","volume":"118","author":"J Andringa","year":"2025","unstructured":"Andringa J, Baptista M, Santos BF (2025) Counterfactual explanations for remaining useful life estimation within a bayesian framework. Inform fusion 118:1\u201315. https:\/\/doi.org\/10.1016\/j.inffus.2025.102972","journal-title":"Inform fusion"},{"issue":"3","key":"9840_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3654933","volume":"2","author":"S An","year":"2024","unstructured":"An S, Cao Y (2024) Counterfactual explanation at will, with zero privacy leakage. Proc ACM Manag Data 2(3):1\u201329. https:\/\/doi.org\/10.1145\/3654933","journal-title":"Proc ACM Manag Data"},{"key":"9840_CR10","doi-asserted-by":"publisher","first-page":"5161","DOI":"10.1007\/s11263-025-02422-6","volume":"133S","author":"G Atigh","year":"2025","unstructured":"Atigh G, Nargang S, Keller-Ressel M, Mettes P (2025) SimZSL: Zero-shot learning beyond a pre-defined sematic embedding space. Int J Comput Vision 133S:5161\u20135177. https:\/\/doi.org\/10.1007\/s11263-025-02422-6","journal-title":"Int J Comput Vision"},{"key":"9840_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-025-07587-w","author":"L Ayash","year":"2025","unstructured":"Ayash L, Algarni A, Alqahtani O (2025) Advancements in feature selection and extraction methods for text mining: a review. Discov Appl Sci. https:\/\/doi.org\/10.1007\/s42452-025-07587-w","journal-title":"Discov Appl Sci"},{"key":"9840_CR12","doi-asserted-by":"publisher","unstructured":"Bau D, Zhou B, Khosla K, Oliva A, Torralba A (2017) Network dissection: Quantifying interpretability of deep visual representations, Computer vision and pattern recognition. 1\u20139. https:\/\/doi.org\/10.48550\/arXiv.1704.05796","DOI":"10.48550\/arXiv.1704.05796"},{"issue":"22","key":"9840_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s44204-024-00238-8","volume":"4","author":"JC Bjerring","year":"2025","unstructured":"Bjerring JC, Mainz J, Munch L (2025) Deep learning models and the limits of explainable artificial intelligence. Asian J Philos 4(22):1\u201326. https:\/\/doi.org\/10.1007\/s44204-024-00238-8","journal-title":"Asian J Philos"},{"key":"9840_CR14","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/s11750-024-00670-2","volume":"32","author":"D Brughmans","year":"2024","unstructured":"Brughmans D, Melis L, Martens D (2024) Disagreement amongst counterfactual explanations: how transparency can be misleading. TOP 32:429\u2013462. https:\/\/doi.org\/10.1007\/s11750-024-00670-2","journal-title":"TOP"},{"issue":"140","key":"9840_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-024-10746-x","volume":"57","author":"N Cang","year":"2024","unstructured":"Cang N, Qiu F, Xue S, Jia Z, Guo D, Zhang z, Li W (2024) New discrete-time zeroing neural network for solving time-dependent linear equation with boundary constraint. Artif Intell Rev 57(140):1\u201324. https:\/\/doi.org\/10.1007\/s10462-024-10746-x","journal-title":"Artif Intell Rev"},{"issue":"1","key":"9840_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.3390\/app14010303","volume":"14","author":"Y Cao","year":"2024","unstructured":"Cao Y, Pu J (2024) Novel zeroing neural network control scheme for tracked mobile robot based on an extended state observer. Appl Sci 14(1):303. https:\/\/doi.org\/10.3390\/app14010303","journal-title":"Appl Sci"},{"issue":"8","key":"9840_CR17","doi-asserted-by":"publisher","first-page":"832","DOI":"10.3390\/electronics8080832","volume":"MDP","author":"D Carvalho","year":"2019","unstructured":"Carvalho D, Pereira E, Cardoso JS (2019) Machine Learning Interpretability: A Survey on Methods and Metrics. Electronics MDP(8):832. https:\/\/doi.org\/10.3390\/electronics8080832","journal-title":"Electronics"},{"key":"9840_CR23","doi-asserted-by":"publisher","unstructured":"C Covert I, Lundberg S, Lee S (2022) I Feature Removal Is A Unifying Principle For Model Explanation Methods 1\u201325 https:\/\/doi.org\/10.48550\/arXiv.2011.03623","DOI":"10.48550\/arXiv.2011.03623"},{"issue":"12","key":"9840_CR18","doi-asserted-by":"publisher","first-page":"228","DOI":"10.3390\/fi12120228","volume":"12","author":"P Ce","year":"2020","unstructured":"Ce P, Tie B (2020) An analysis method for interpretability of CNN text classication model. Future internet MDPI 12(12):228. https:\/\/doi.org\/10.3390\/fi12120228","journal-title":"Future internet MDPI"},{"issue":"1","key":"9840_CR19","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41746-022-00699-2","volume":"5","author":"H Chen","year":"2022","unstructured":"Chen H, Gomez C, Huang C, M, Unberath M (2022) Explainable medical imaging AI needs human-centered design: Guidelines and evidence from a systematic review. NPJ Digit Med 5(1):156. https:\/\/doi.org\/10.1038\/s41746-022-00699-2","journal-title":"NPJ Digit Med"},{"issue":"7","key":"9840_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1049\/ell2.13162","volume":"60","author":"X Chen","year":"2024","unstructured":"Chen X, Kong Y, Zeng X, Yin J (2024) Milne-hamming discretized zeroing neural networks for solving time-varying linear systems. Electron Lett 60(7):1\u20134. https:\/\/doi.org\/10.1049\/ell2.13162","journal-title":"Electron Lett"},{"key":"9840_CR21","doi-asserted-by":"publisher","unstructured":"Choudhary C, Vyas N, Lilhore UK (2023) An optimized sign language recognition using convolutional neural networks (CNNs) and Tensor-Flow. In Proceedings of the 2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS). https:\/\/doi.org\/10.1109\/ICTACS59847.2023.10390276","DOI":"10.1109\/ICTACS59847.2023.10390276"},{"key":"9840_CR22","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-6602601\/v1","author":"C Constantinou","year":"2025","unstructured":"Constantinou C (2025) Out-of-distribution detection with attention head masking for multi-modal document classification. Preprint. https:\/\/doi.org\/10.21203\/rs.3.rs-6602601\/v1","journal-title":"Preprint"},{"key":"9840_CR24","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1414637","author":"A Darolia","year":"2024","unstructured":"Darolia A, Chhillar RS, Alhussein M, Dalal S, Aurangzeb K, Lilhore UK (2024) Enhanced cardiovascular disease prediction through self-improved Aquila optimized feature selection in quantum neural network & LSTM model. Front Med. https:\/\/doi.org\/10.3389\/fmed.2024.1414637","journal-title":"Front Med"},{"issue":"8","key":"9840_CR25","doi-asserted-by":"publisher","first-page":"1573","DOI":"10.1109\/TCAD.2020.3022330","volume":"40","author":"P Das","year":"2021","unstructured":"Das P, Kapoor H (2021) Nzespa: Anear-3D-memory zero skipping parallel accelerator for CNNs. IEEE Trans Comput Aided Des Integr Circuits Syst 40(8):1573\u20131585. https:\/\/ieeexplore.ieee.org\/document\/9187865","journal-title":"IEEE Trans Comput Aided Des Integr Circuits Syst"},{"key":"9840_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2025.101669","volume":"42","author":"J Debnath","year":"2025","unstructured":"Debnath J, Khondakar-Pranta ASU, Hossain A, Sakib A, Rahman H, Ahmed MR, Reza AW (2025) LMVT: a hybrid vision transformer with attention mechanisms for efficient and explainable lung cancer diagnosis. Inf Med Unlocked 42:101669. https:\/\/doi.org\/10.1016\/j.imu.2025.101669","journal-title":"Inf Med Unlocked"},{"key":"9840_CR27","unstructured":"Ding X, Ding G, Zhou X, Guo Y, Han J, Liu J (2019) Global sparse momentum sgd for pruning very deep neural networks, in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 6379\u20136391. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/f34185c4ca5d58e781d4f14173d41e5d-Paper.pdf"},{"key":"9840_CR28","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.neunet.2023.09.030","volume":"168","author":"H Dou","year":"2023","unstructured":"Dou H, Shen F, Zhao J, Mu X (2023) Understanding neural network through neuron level visualization. Neural Netw 168:484\u2013495. https:\/\/doi.org\/10.1016\/j.neunet.2023.09.030","journal-title":"Neural Netw"},{"key":"9840_CR29","doi-asserted-by":"publisher","first-page":"187947","DOI":"10.1109\/ACCESS.2024.3432776","volume":"12","author":"M Dutt","year":"2024","unstructured":"Dutt M, Goodwin M, Omlin CW (2024) An interpretable deep learning-based feature reduction in video-based human activity recognition. IEEE Access 12:187947\u2013187963. https:\/\/doi.org\/10.1109\/ACCESS.2024.3432776","journal-title":"IEEE Access"},{"issue":"7","key":"9840_CR30","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12071670","volume":"12","author":"G Elkhawaga","year":"2023","unstructured":"Elkhawaga G, Elzeki O, Abuelkheir M, Reichert M (2023) Evaluating explainable artificial intelligence methods based on feature elimination: a functionality-grounded approach. Electronics 12(7):1670. https:\/\/doi.org\/10.3390\/electronics12071670","journal-title":"Electronics"},{"key":"9840_CR31","doi-asserted-by":"publisher","unstructured":"Ferrao J, Mikaelson L, Pepper K, Antolin NPC (2025) Self-ablating transformers: more interpretability, less sparsity, machine learning, 1\u201315. https:\/\/doi.org\/10.48550\/arXiv.2505.00509","DOI":"10.48550\/arXiv.2505.00509"},{"issue":"3","key":"9840_CR33","doi-asserted-by":"publisher","DOI":"10.3390\/app12031427","volume":"12","author":"W Freeborough","year":"2022","unstructured":"Freeborough W, Van-Zyl T (2022) Investigating explainability methods in recurrent neural network architectures for financial time series data. MDPI: Appl Sci 12(3):1427. https:\/\/doi.org\/10.3390\/app12031427","journal-title":"MDPI: Appl Sci"},{"key":"9840_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03358-1","author":"N Gaggion","year":"2024","unstructured":"Gaggion N, Mosquera C, Mansilla L, Saidman JM, Aineseder M, Milone DH, Ferrante E (2024) CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images. Sci Data. https:\/\/doi.org\/10.1038\/s41597-024-03358-1","journal-title":"Sci Data"},{"key":"9840_CR35","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.neucom.2024.128972","volume":"617","author":"B Gao","year":"2024","unstructured":"Gao B, Spratling MW (2024) Filter competition results in more robust convolutional neural networks. Neurocomputing 617:45\u201358. https:\/\/doi.org\/10.1016\/j.neucom.2024.128972","journal-title":"Neurocomputing"},{"issue":"6","key":"9840_CR36","doi-asserted-by":"publisher","first-page":"3172","DOI":"10.1109\/JSEN.2019.2958787","volume":"20","author":"J Grezmak","year":"2020","unstructured":"Grezmak J, Zhang J, Wang P, Loparo KA, Gao RX (2020) Interpretable convolutional neural network through layer-wise relevance propagation for machine fault diagnosis. IEEE Sens J 20(6):3172\u20133181. https:\/\/doi.org\/10.1109\/JSEN.2019.2958787","journal-title":"IEEE Sens J"},{"key":"9840_CR37","doi-asserted-by":"publisher","first-page":"2770","DOI":"10.1007\/s10618-022-00831-6","volume":"38","author":"R Guidotti","year":"2022","unstructured":"Guidotti R (2022) Counterfactual explanations and how to find them: literature review and benchmarking. Data Min Knowl Discov 38:2770\u20132824. https:\/\/doi.org\/10.1007\/s10618-022-00831-6","journal-title":"Data Min Knowl Discov"},{"issue":"5","key":"9840_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D (2018) A survey of methods for explaining black box models. ACM Comput Surv 51(5):1\u201342. https:\/\/doi.org\/10.1145\/3236009","journal-title":"ACM Comput Surv"},{"key":"9840_CR131","doi-asserted-by":"publisher","unstructured":"Gunasekaran A, Chen M, Hill R, McCabe K (2023) Method agnostic model class reliance (mamcr) explanation of multiple machine learning models. In: International Conference on soft computing and its engineering applications, Springer: 56\u201371. https:\/\/doi.org\/10.1007\/978-3-031-27609-5_5","DOI":"10.1007\/978-3-031-27609-5_5"},{"issue":"503","key":"9840_CR132","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-024-02810-8","volume":"5","author":"P GunasekaranA, Pritesh Mistry","year":"2024","unstructured":"Gunasekaran A, Pritesh Mistry P, Minsi Chen M (2024) Which Explanation Should be Selected: A Method Agnostic Model Class Reliance Explanation for Model and Explanation Multiplicity. SN Comput Sci 5(503):1\u201320. https:\/\/doi.org\/10.1007\/s42979-024-02810-8","journal-title":"SN Comput Sci"},{"key":"9840_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-024-11026-4","volume":"58","author":"D Guo","year":"2025","unstructured":"Guo D, Zhang C, Cang N, Zhang X, Xiao L, ZSun Z (2025) New fuzzy zeroing neural network with noise suppression capability for time-varying linear equation solving. Artif Intell Rev 58:1\u201320. https:\/\/doi.org\/10.1007\/s10462-024-11026-4","journal-title":"Artif Intell Rev"},{"key":"9840_CR39","unstructured":"Guo T, GuoS, Zhang J, Xu W, Wang J (2022) Efficient attribution unlearning: towards selective removal of input attributes from feature representations. Mach Learn, 1\u20139, https:\/\/arxiv.org\/abs\/2202.13295\u2019"},{"issue":"11","key":"9840_CR41","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc8110149","volume":"8","author":"SU Hamida","year":"2024","unstructured":"Hamida SU, Chowdhry MJM, Chakraborty NR, Biswas K, Sami S (2024) Exploring the landscape of explainable artificial intelligence(XAI): MSPI: a systematic review of techniques and applications. Big Data Cogn Comput 8(11):149. https:\/\/doi.org\/10.3390\/bdcc8110149","journal-title":"Big Data Cogn Comput"},{"key":"9840_CR43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.17613","author":"S Hellemans","year":"2025","unstructured":"Hellemans S, Algaba A, Verboven S, Ginis V (2025) Flexible counterfactual explanations with generative models. Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.2502.17613","journal-title":"Mach Learn"},{"key":"9840_CR44","doi-asserted-by":"publisher","unstructured":"Henna S, Alcaraz JML (2022) From interpretable filters to predictions of convolutional neural networks with explainable artificial intelligence, IEEE Transactions on artificial intelligence, arXiv:2207.12958v1 [cs.LG] 26 Jul 2022, 1\u201313. https:\/\/doi.org\/10.48550\/arXiv.2207.12958","DOI":"10.48550\/arXiv.2207.12958"},{"key":"9840_CR42","doi-asserted-by":"publisher","unstructured":"He Y, Kang G, Dong X, Fu Y, Yang Y (2018) Soft filter pruning for accelerating deep convolutional neural networks, in Proc. Int. Joint Conf. Artif. Intell., 2234\u20132240. https:\/\/doi.org\/10.48550\/arXiv.1808.06866","DOI":"10.48550\/arXiv.1808.06866"},{"key":"9840_CR45","unstructured":"Hondru V, Croitooru FA, Minaee S, Ionescu RT, Sebe N (2024) Masked image modeling: A survey, 1\u201341, arXiv:2408.06687v1 [cs.CV] 13 Aug 2024"},{"key":"9840_CR46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.05997","author":"J Hou","year":"2024","unstructured":"Hou J, Xu J, Chen H (2024) Concept-attention whitening for interpretable skin lesion diagnosis. Comput Vis Pattern Recognit. https:\/\/doi.org\/10.48550\/arXiv.2404.05997","journal-title":"Comput Vis Pattern Recognit"},{"key":"9840_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130485","volume":"28","author":"H Huang","year":"2025","unstructured":"Huang H, Pao HK (2025) Interpretable deep model pruning, Science Direct. Neurocomputing 28:647. https:\/\/doi.org\/10.1016\/j.neucom.2025.130485","journal-title":"Neurocomputing"},{"key":"9840_CR49","doi-asserted-by":"publisher","unstructured":"Huang PY, Sharma V, Xu H, Ryali C, Fan H, Li Y, Li S, Ghosh G, Malik J, Feichtenhofer C (2023) MAViL: Masked Audio-Video Learners. In: Proceedings of NeurIPS. 36:20371\u201320393. https:\/\/doi.org\/10.48550\/arXiv.2212.08071","DOI":"10.48550\/arXiv.2212.08071"},{"key":"9840_CR47","doi-asserted-by":"publisher","unstructured":"Huang Z, Li Y (2020) Interpretable and accurate fine grained recognition via region grouping. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2. https:\/\/doi.org\/10.48550\/arXiv.2005.10411","DOI":"10.48550\/arXiv.2005.10411"},{"issue":"3","key":"9840_CR50","doi-asserted-by":"publisher","first-page":"652","DOI":"10.3390\/ai4030034","volume":"4","author":"T Hulsen","year":"2023","unstructured":"Hulsen T (2023) Explainable artificial intelligence (XAI): concepts and challenges in healthcare. AI 4(3):652\u2013666. https:\/\/doi.org\/10.3390\/ai4030034","journal-title":"AI"},{"key":"9840_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.health.2024.100340","volume":"5","author":"T Islam","year":"2024","unstructured":"Islam T, Hafiz S, Jim JR, Kabir M, Mridha MF (2024) A systematic review of deep learning data augmentation in medical imaging: recent advances and future research directions. Healthc analytics 5:1\u201318. https:\/\/doi.org\/10.1016\/j.health.2024.100340","journal-title":"Healthc analytics"},{"key":"9840_CR52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.11509","author":"S Jain","year":"2025","unstructured":"Jain S, Sangroya A, Vig L (2025) DifCluE: Generating counterfactual explanations with diffusion autoencoders and modal clustering. Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.2502.11509","journal-title":"Mach Learn"},{"issue":"23","key":"9840_CR53","doi-asserted-by":"publisher","DOI":"10.3390\/math10234490","volume":"10","author":"H Jerbi","year":"2022","unstructured":"Jerbi H, Alharbi H, Omri M, Ladhar L, Simos TE, Mourtas S D, Katsikis VN (2022) Towards higher-order zeroing neural network dynamics for solving time-varying algebraic Riccati equations. Mathematics 10(23):4490. https:\/\/doi.org\/10.3390\/math10234490","journal-title":"Mathematics"},{"key":"9840_CR54","doi-asserted-by":"publisher","unstructured":"Jesus S, Bel\u00e9m C, Balayan V, Bento J, Saleiro P, Bizarro P, Gama J (2021) How can I choose an explainer? In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Virtual, New York, NY, USA, 805\u2013815. [Google Scholar]. https:\/\/doi.org\/10.1145\/3442188.3445941","DOI":"10.1145\/3442188.3445941"},{"key":"9840_CR55","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1038\/s42256-025-01000-2","volume":"7","author":"J Kauffmann","year":"2024","unstructured":"Kauffmann J, Dippel J, Ruff L, Samek W, Muller K, Montavon G (2024) Explainable AI reveals clever Hans effects in unsupervised learning models. Nat Mach Learn 7:412\u2013422. https:\/\/doi.org\/10.1038\/s42256-025-01000-2","journal-title":"Nat Mach Learn"},{"issue":"5","key":"9840_CR56","doi-asserted-by":"publisher","first-page":"459","DOI":"10.55730\/1300-0152.2761","volume":"49","author":"Y Kaya","year":"2025","unstructured":"Kaya Y, G\u00fcrsoy E (2025) A review of deep learning architectures for plant disease detection. Turkish J Biology 49(5):459\u2013497. https:\/\/doi.org\/10.55730\/1300-0152.2761","journal-title":"Turkish J Biology"},{"issue":"1","key":"9840_CR57","doi-asserted-by":"publisher","first-page":"48","DOI":"10.14445\/22312803\/IJCTT-V72I1P108","volume":"12","author":"P Keyur","year":"2024","unstructured":"Keyur P (2024) Lawful and righteous considerations for the use of artificial intelligence in public health. Int J Comput Trends Technol 12(1):48\u201352. https:\/\/doi.org\/10.14445\/22312803\/IJCTT-V72I1P108","journal-title":"Int J Comput Trends Technol"},{"issue":"232","key":"9840_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-025-11215-9","volume":"58","author":"FS Khan","year":"2025","unstructured":"Khan FS, Mazhar SS, Mazher K, Alsaleh DA, Mazhar A (2025) Model-agnosic explainable artificial intelligence methods in financial: a systematic review, recent developments, limitations, challenges and future directions. Artif Intell Rev 58(232):1\u201365. https:\/\/doi.org\/10.1007\/s10462-025-11215-9","journal-title":"Artif Intell Rev"},{"key":"9840_CR59","doi-asserted-by":"publisher","unstructured":"Kim NJ, Kim H (2020) Mask-soft filter pruning for lightweight CNN inference, IEEE: 2020 International SoC design, conference(ISOCC), 1\u201320. https:\/\/doi.org\/10.1109\/ISOCC50952.2020.9333054","DOI":"10.1109\/ISOCC50952.2020.9333054"},{"key":"9840_CR60","doi-asserted-by":"publisher","first-page":"5279","DOI":"10.1109\/TMM.2022.3189496","volume":"25","author":"NJ Kim","year":"2022","unstructured":"Kim NJ, Kim H (2022) FP-AGL: filter pruning with adaptive gradient learning for accelerating deep convolutional neural networks. IEEE Trans Multimedia 25:5279\u20135290. https:\/\/doi.org\/10.1109\/TMM.2022.3189496","journal-title":"IEEE Trans Multimedia"},{"key":"9840_CR61","doi-asserted-by":"publisher","unstructured":"Kodirov E, Xiang T, Shaogang (2017) Semantic autoencoder for zero-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2:3174\u20133183. https:\/\/doi.org\/10.48550\/arXiv.1704.08345","DOI":"10.48550\/arXiv.1704.08345"},{"key":"9840_CR62","doi-asserted-by":"publisher","DOI":"10.1007\/s12599-024-00922-2","author":"S Kruschel","year":"2025","unstructured":"Kruschel S, Hambauer N, Weinzieri S, Zilker S, Kraus M, Zschech P (2025) Challenging the performance-interpretability trade-off: An evaluation of interpretable machine leaning models. Bus Inform Syst Eng. https:\/\/doi.org\/10.1007\/s12599-024-00922-2","journal-title":"Bus Inform Syst Eng"},{"issue":"9","key":"9840_CR64","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3555803","volume":"55","author":"B Li","year":"2022","unstructured":"Li B, Qi P, Liu B, Di S, Liu J, Pei J, Yi J, Zhou B (2022) Trustworthy AI: from principles to practices. ACM Comput Surv 55(9):1\u201346. https:\/\/doi.org\/10.1145\/3555803","journal-title":"ACM Comput Surv"},{"issue":"26","key":"9840_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-024-18182-3","volume":"83","author":"UK Lilhore","year":"2024","unstructured":"Lilhore UK (2024) Unveiling the prevalence and risk factors of early stage postpartum depression: a hybrid deep learning approach. Multimedia Tools Appl 83(26):1\u201335. https:\/\/doi.org\/10.1007\/s11042-024-18182-3","journal-title":"Multimedia Tools Appl"},{"key":"9840_CR70","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-95311-4","volume":"15","author":"UK Lilhore","year":"2025","unstructured":"Lilhore UK, Sharma YK, Shukla BK, Vadlamudi MN, Simaiya S, Alroobaea R, Alsafyani M, Bagasah AM (2025) Hybrid convolutional neural network and bi-LSTM model with EfficientNet-B0 for high-accuracy breast cancer detection and classification. Sci Rep 15:12082. https:\/\/doi.org\/10.1038\/s41598-025-95311-4","journal-title":"Sci Rep"},{"key":"9840_CR66","doi-asserted-by":"publisher","unstructured":"Li M, Janson L (2024a) Optimal ablation for interpretability. In D. Proceedings Advances in Neural Information Processing Systems (NeurIPS 2024), 1\u201345. https:\/\/doi.org\/10.48550\/arXiv.2409.09951","DOI":"10.48550\/arXiv.2409.09951"},{"issue":"10","key":"9840_CR68","doi-asserted-by":"publisher","first-page":"14905","DOI":"10.1109\/TITS.2024.3393634","volume":"25","author":"M Li","year":"2024","unstructured":"Li M, Sun H, Huang Y, Chen H (2024b) SVCE: shapely value guided counterfactual explanation for machine learning-based autonomlus driving. IEEE Trans Intell Transp Syst 25(10):14905\u201314916. https:\/\/doi.org\/10.1109\/TITS.2024.3393634","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"9840_CR71","doi-asserted-by":"publisher","unstructured":"Lin C, Covert I, Lee SI (2023) On the robustness of removal-based feature attribution, NIPS \u201823: Proceedings of the 37th International Conference on Neural Information Processing Systems, 3486, 79613\u201379666. https:\/\/doi.org\/10.48550\/arXiv.2306.07462","DOI":"10.48550\/arXiv.2306.07462"},{"issue":"12","key":"9840_CR75","doi-asserted-by":"publisher","first-page":"8157","DOI":"10.1109\/TPAMI.2024.3399936","volume":"46","author":"S Liu","year":"2024","unstructured":"Liu S, Song J, Zhou Y, Yu N, Chen K, Feng Z (2024) Interaction pattern disentangling for multi-agent reinforcement learning. IEEE Trans Pattern Anal Mach Intell 46(12):8157\u20138172. https:\/\/ieeexplore.ieee.org\/document\/10529613","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9840_CR73","doi-asserted-by":"publisher","unstructured":"Liu T, Xie X (2021) and Zhang.Y zkCNN: Zero knowledge proofs for convolutional neural network predictions and accuracy. In CCS \u201821: Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 2968\u20132985. ACM. https:\/\/doi.org\/10.1145\/3460120.3484764","DOI":"10.1145\/3460120.3484764"},{"key":"9840_CR76","doi-asserted-by":"publisher","unstructured":"Liu X, Wang X, Matwin S (2018) Interpretable deep convolutional neural networks via meta-learning. Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.1802.00560","DOI":"10.48550\/arXiv.1802.00560"},{"issue":"8","key":"9840_CR74","doi-asserted-by":"publisher","first-page":"2717","DOI":"10.1007\/s00521-022-07689-1","volume":"35","author":"Y Liu","year":"2023","unstructured":"Liu Y, Miyazaki J (2023) Challenges in scaling interpretable models for complex tasks. Neural Comput Appl 35(8):2717\u20132735. https:\/\/doi.org\/10.1007\/s00521-022-07689-1","journal-title":"Neural Comput Appl"},{"issue":"11","key":"9840_CR65","doi-asserted-by":"publisher","first-page":"6881","DOI":"10.1109\/TIV.2024.3390426","volume":"9","author":"X Li","year":"2024","unstructured":"Li X, Goa X, Wang C, Wang Q, Li B, Wan K (2024a) Relevance inference based on direct counterfactual explanation to deep networks for intelligent decision-making. IEEE Trans Intell Veh 9(11):6881\u20136897. https:\/\/doi.org\/10.1109\/TIV.2024.3390426","journal-title":"IEEE Trans Intell Veh"},{"key":"9840_CR77","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1705.07874","volume":"24","author":"S Lundberg","year":"2023","unstructured":"Lundberg S, Lee S (2023) SHAP: A unified approach to explain model outputs. J Mach Learn Res 24:1\u201342. https:\/\/doi.org\/10.48550\/arXiv.1705.07874","journal-title":"J Mach Learn Res"},{"key":"9840_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.engappai.2025.110363","volume":"149","author":"N Mehdiyev","year":"2025","unstructured":"Mehdiyev N, Majlatow M, Fettke F (2025) Integrating permutation feature importance with control prediction for robust explainable artificial intelligence in predictive process monitoring. Eng Appl Artif Intell 149:1\u201326. https:\/\/doi.org\/10.1016\/j.engappai.2025.110363","journal-title":"Eng Appl Artif Intell"},{"key":"9840_CR81","doi-asserted-by":"publisher","unstructured":"Molchanov P, Tyree S, Karras T, Aila T, Kautz J (2017) Pruning convolutional neural networks for resource efficient inference. Mach Learn 1\u201317. https:\/\/doi.org\/10.48550\/arXiv.1611.06440","DOI":"10.48550\/arXiv.1611.06440"},{"key":"9840_CR82","unstructured":"Moniri B, Lee D, Hassani H, Dobriban E (2025) A theory of non-linear feature learning with one gradient step in two-layer neural networks, 1\u201366. https:\/\/arxiv.org\/pdf\/2310.07891"},{"key":"9840_CR83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.11397","author":"P Morala","year":"2023","unstructured":"Morala P, Cifuentes JA, Lillo RE, Ucar I (2023) NN2Poly: Apolynomial representation for deep feed-forward artificial neural networks. Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.2112.11397","journal-title":"Mach Learn"},{"key":"9840_CR84","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1016\/j.csbj.2024.08.005","volume":"24","author":"D Muhammad","year":"2024","unstructured":"Muhammad D, Bendechache M (2024) Unveiling the black box: A systematic review of explainable artificial intelligence in medical image analysis. Comput Struct Biotechnol J 24:542\u2013560. https:\/\/doi.org\/10.1016\/j.csbj.2024.08.005","journal-title":"Comput Struct Biotechnol J"},{"key":"9840_CR86","doi-asserted-by":"publisher","first-page":"102412","DOI":"10.1016\/j.inffus.2024.102412","volume":"108","author":"E Nasarian","year":"2024","unstructured":"Nasarian E, Alizadehsani R, Acharya UR, Tsui K-L (2024) Designing interpretable ML system to enhance trust in healthcare: A systematic review to proposed responsible clinician\u2013AI collaboration framework. Inform Fusion 108:102412. https:\/\/doi.org\/10.1016\/j.inffus.2024.102412","journal-title":"Inform Fusion"},{"issue":"10","key":"9840_CR85","doi-asserted-by":"publisher","first-page":"18355","DOI":"10.1109\/TNNLS.2025.3580118","volume":"36","author":"S-H Na","year":"2025","unstructured":"Na S-H, Lee S-W (2025) Counterfactual explanation through latent adjustment in disentangled space of diffusion model. IEEE Trans Neural Networks Learn Syst 36(10):18355\u201318368. https:\/\/doi.org\/10.1109\/TNNLS.2025.3580118","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"9840_CR88","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-030-28954-6_4","volume-title":"Understanding neural networks via feature visualization: A survey, in Explainable AI: interpreting, explaining and visualizing deep learning","author":"A Nguyen","year":"2019","unstructured":"Nguyen A, Yosinski J, Clune J (2019) Understanding neural networks via feature visualization: A survey, in Explainable AI: interpreting, explaining and visualizing deep learning. Springer, pp 55\u201376. https:\/\/doi.org\/10.1007\/978-3-030-28954-6_4"},{"issue":"4","key":"9840_CR90","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/MSP.2022.3142719","volume":"39","author":"IE Nielsen","year":"2022","unstructured":"Nielsen IE, Dera D, Rasool G, Ramachandran RP, Bouaynaya NC (2022) Robust explainability: A tutorial on gradient-based attribution methods for deep neural networks. IEEE Signal Process Mag 39(4):73\u201384. https:\/\/doi.org\/10.1109\/MSP.2022.3142719","journal-title":"IEEE Signal Process Mag"},{"key":"9840_CR89","doi-asserted-by":"crossref","unstructured":"Nielsen IE, Grundeland E, Snedeker J, Ramachandran RP, Rasool G (2023) Targeted background removal creates interpretable feature visualizations, 2023 IEEE 66 international midwest symposium on circuits and systems(MWSCAS), 1\u201312. https:\/\/ieeexplore.ieee.org\/document\/10405878","DOI":"10.1109\/MWSCAS57524.2023.10405878"},{"key":"9840_CR91","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1054401","volume":"14","author":"S Ogbomo-Harmitt","year":"2023","unstructured":"Ogbomo-Harmitt S, Muffoletto M, Zeidan A, Qureshi A, King AP, Aslanidi O (2023) Exploring interpretability in deep learning prediction of successful ablation therapy for atrial fibrillation. Front Physiol 14:1054401. https:\/\/doi.org\/10.3389\/fphys.2023.1054401","journal-title":"Front Physiol"},{"key":"9840_CR92","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-74993-2","volume":"14","author":"V Pandey","year":"2024","unstructured":"Pandey V, Lilhore UK, Walia R, Alroobaea R, Alsafyani M, Bagasah AM, Algarni S (2024) Enhancing heart disease classification with M2MASC and CNN-BiLSTM integration for improved accuracy. Sci Rep 14:74993. https:\/\/doi.org\/10.1038\/s41598-024-74993-2","journal-title":"Sci Rep"},{"issue":"7","key":"9840_CR93","doi-asserted-by":"publisher","first-page":"443","DOI":"10.3390\/a18070443","volume":"18","author":"D Pelosi","year":"2025","unstructured":"Pelosi D, Cacciagrano D, Piangerelli M (2025) Explainability and interpretability in concept and data drift: A systematic literature review. Algorithms Basel 18(7):443. https:\/\/doi.org\/10.3390\/a18070443","journal-title":"Algorithms Basel"},{"key":"9840_CR95","doi-asserted-by":"publisher","unstructured":"Pochinkov N, Pasero B, Shibayama S (2024) Investigating neuron Ablaion in attention heads: The case for peak activation centering, The 2nd World Conference on eXplainable Artificial Intelligence, 1\u20139. https:\/\/doi.org\/10.48550\/arXiv.2408.17322","DOI":"10.48550\/arXiv.2408.17322"},{"issue":"1","key":"9840_CR96","doi-asserted-by":"publisher","DOI":"10.3390\/biomedinformatics5010010","volume":"5","author":"L Prokopiou","year":"2025","unstructured":"Prokopiou L, Spyridonos P (2025) Highlighting the advanced capabilities and the computational efficiency of DeepLabV3\u2009+\u2009in medical image segmentation: An ablation study. MDPI BioMedInformatics 5(1):10. https:\/\/doi.org\/10.3390\/biomedinformatics5010010","journal-title":"MDPI BioMedInformatics"},{"key":"9840_CR97","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2024.106166","volume":"173","author":"D Qin","year":"2024","unstructured":"Qin D, Amariucai G, Qiao D, Guan Y, Fu S (2024) A comprehensive and reliable feature attribution method: Double-side remove ad reconstruct(DoRaR). Neural Netw 173:1\u201320. https:\/\/doi.org\/10.1016\/j.neunet.2024.106166","journal-title":"Neural Netw"},{"issue":"4","key":"9840_CR98","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.3390\/s25041033","volume":"25","author":"R Raj","year":"2025","unstructured":"Raj R, Kos A (2025) An extensive study of convolutional neural networks: Applications in Computer Vision for improved Robotics perceptions. Sensors Basel 25(4):1033. https:\/\/doi.org\/10.3390\/s25041033","journal-title":"Sensors Basel"},{"key":"9840_CR99","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2025.104158","volume":"25","author":"S Ramya","year":"2025","unstructured":"Ramya S, Srinath S, Tuppad P (2025) Advanced temporal deep learning framework for enhanced predictive modeling in industrial treatment systems. Results Eng 25:104158. https:\/\/doi.org\/10.1016\/j.rineng.2025.104158","journal-title":"Results Eng"},{"key":"9840_CR100","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ACCESS.2025.3543277","volume":"13","author":"MM Rashid","year":"2025","unstructured":"Rashid MM, Osman MH, Sharif K, Y, Zulzalil H (2025) Interpretable deep learning for efficient code smell prioritization in software development. IEEE Access 13:1\u201322. https:\/\/doi.org\/10.1109\/ACCESS.2025.3543277","journal-title":"IEEE Access"},{"issue":"2","key":"9840_CR101","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3685678","volume":"19","author":"Y Rong","year":"2025","unstructured":"Rong Y, Wang G, Feng O, Liu N, Liu Z, Kasneci E, Hu X (2025) Efficient GNN explanation via learning removal-based attribution. ACM Trans Knowl discovery data 19(2):1\u201323. https:\/\/doi.org\/10.1145\/3685678","journal-title":"ACM Trans Knowl discovery data"},{"key":"9840_CR102","doi-asserted-by":"publisher","unstructured":"Sabih M, Hanning F, Teich J (2022) DyFiP: Explanable AI-based dynamic filter pruning convolutional neural networks, EuroMLSys \u201822: Proceedings of the 2nd European Workshop on Machine Learning and Systems,109\u2013115, ACM. https:\/\/doi.org\/10.1145\/3517207.3526982","DOI":"10.1145\/3517207.3526982"},{"issue":"01","key":"9840_CR103","doi-asserted-by":"publisher","first-page":"67","DOI":"10.48550\/arXiv.2506.20359","volume":"07","author":"D Samarasingghage","year":"2025","unstructured":"Samarasingghage D, Gulabani D (2025) Towards interpretable and efficient feature selection in trajectory datasets: A taxonomic approach. J Artif Intell metabeuristics(JAIM) 07(01):67\u201377. https:\/\/doi.org\/10.48550\/arXiv.2506.20359","journal-title":"J Artif Intell metabeuristics(JAIM)"},{"key":"9840_CR104","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.dajour.2024.100489","volume":"12","author":"NA Saputra","year":"2024","unstructured":"Saputra NA, Riza LS, Setiawan A, Hamidah I (2024) A systematic review for classification and selection of deep learning methods. Decis analytics J 12:1\u201317. https:\/\/doi.org\/10.1016\/j.dajour.2024.100489","journal-title":"Decis analytics J"},{"key":"9840_CR105","doi-asserted-by":"publisher","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, 618\u2013626. https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"9840_CR133","doi-asserted-by":"publisher","first-page":"12082","DOI":"10.1038\/s41598-025-95311-4","volume":"15","author":"LUK Sharma","year":"2025","unstructured":"Sharma LUK, Shukla YK, K B, Vadlamudi MN, Simaiya S, Alroobaea R, Alsafyani M, Bagasah AM (2025) Hybrid convolutional neural network and bi-LSTM model with EfficientNet-B0 for high-accuracy breast cancer detection and classification. Sci Rep 15:12082. https:\/\/doi.org\/10.1038\/s41598-025-95311-4","journal-title":"Sci Rep"},{"key":"9840_CR108","doi-asserted-by":"publisher","unstructured":"Singh A, Chaudhuri K, Singh D M. S, and, Chattopadhyay S (2024) Integrated CAM: Adaptive layer fusion for comprehensive interpretation of CNNs, Computer vision and pattern recognition. 1\u201322. https:\/\/doi.org\/10.48550\/arXiv.2412.01354","DOI":"10.48550\/arXiv.2412.01354"},{"key":"9840_CR107","doi-asserted-by":"publisher","first-page":"3741","DOI":"10.1016\/j.procs.2025.04.629","volume":"258","author":"S Singh","year":"2025","unstructured":"Singh S, Ahuja NJ (2025) Towards transparent deep learning: assessing model accuracy and interpretability in CNNs. Procedia Comput Sci 258:3741\u20133749. https:\/\/doi.org\/10.1016\/j.procs.2025.04.629","journal-title":"Procedia Comput Sci"},{"issue":"4","key":"9840_CR109","doi-asserted-by":"publisher","first-page":"2505","DOI":"10.1109\/TPAMI.2024.3520899","volume":"47","author":"Y Song","year":"2025","unstructured":"Song Y, Wang W, Sebe N (2025) RankFeat&RankWeight: Rank-1 feature\/weight removal for out-of-distribution detection. IEEE Trans pattern Anal mchine Intell 47(4):2505\u20132519. https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?arnumber=10812065","journal-title":"IEEE Trans pattern Anal mchine Intell"},{"key":"9840_CR110","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01531-5","author":"T Sourget","year":"2025","unstructured":"Sourget T, Hestbek-Moller M, Jimenez-Sanchez A, Xu JJ, Cheplygina V (2025) Mask of truth: model sensitivity to unexpected regions of medical images. J imaging Inf Med. https:\/\/doi.org\/10.1007\/s10278-025-01531-5","journal-title":"J imaging Inf Med"},{"key":"9840_CR111","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051315","author":"L Stepin","year":"2021","unstructured":"Stepin L, Aloso JM, Catala A, Pereira-farina M (2021) A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2021.3051315","journal-title":"IEEE Access"},{"key":"9840_CR112","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-023-46493-2","volume":"13","author":"J Sun","year":"2023","unstructured":"Sun J, Shi W, Giuste FO, Vaghani YS, Tang L, Wang MD (2023b) Improving explainable AI with patch perturbation-based evaluation pipeline: a COVID-19 X-ray image analysis case study. Sci Rep 13:1\u201318. https:\/\/doi.org\/10.1038\/s41598-023-46493-2","journal-title":"Sci Rep"},{"key":"9840_CR114","doi-asserted-by":"publisher","unstructured":"Sun S, Koch LM, Baumgartner C (2023a) Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations? In: International Conference on Medical Image Computing and Computer-Assisted Intervention, 425\u2013434. https:\/\/doi.org\/10.1007\/978-3-031-43895-0_40","DOI":"10.1007\/978-3-031-43895-0_40"},{"issue":"211","key":"9840_CR113","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-024-10804-4","volume":"57","author":"Z Sun","year":"2024","unstructured":"Sun Z, Zhou Y, Tang S, Luo J, Zhao B (2024) Noise suppression zeroing neural network for online solving the time-varying inverse kinematics problem of four-wheel mobile manipulators with external disturbances. Artif Intell Rev 57(211):1\u201324. https:\/\/doi.org\/10.1007\/s10462-024-10804-4","journal-title":"Artif Intell Rev"},{"key":"9840_CR117","unstructured":"Tariq SA, Zia T, Ghafoor M (2025) Towards counterfactual and contrastive explainability and transparency of DCNN image classifiers, Apreprint, 1\u201321, arXiv:2501.06831v1 [cs.CV] Q12 Jan 2025"},{"issue":"1","key":"9840_CR116","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01725-9","volume":"8","author":"EJ Topol","year":"2025","unstructured":"Topol EJ, Rajpurkar P, Shortliffe EH (2025) Artificial intelligence should genuinely support clinical reasoning and decision making to bridge the translational gap. npj Digit Med 8(1):Article 172. https:\/\/doi.org\/10.1038\/s41746-025-01725-9","journal-title":"npj Digit Med"},{"key":"9840_CR118","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.inffus.2021.05.009","volume":"76","author":"G Vilone","year":"2021","unstructured":"Vilone G, Longo L (2021) Notions of explainability and evaluation approaches for explainable artificial intelligence. Inf Fusion 76:89\u2013106. https:\/\/doi.org\/10.1016\/j.inffus.2021.05.009","journal-title":"Inf Fusion"},{"issue":"6","key":"9840_CR119","doi-asserted-by":"publisher","DOI":"10.3390\/app15063077","volume":"16","author":"DG Vincent","year":"2025","unstructured":"Vincent DG, Surantha N (2025) Performance evaluation of convolutional neural network (CNN) for skin cancer detection on edge computing devices. Appl Sci 16(6):3077. https:\/\/doi.org\/10.3390\/app15063077","journal-title":"Appl Sci"},{"issue":"5","key":"9840_CR120","doi-asserted-by":"publisher","first-page":"279","DOI":"10.3390\/biomimetics10050279","volume":"10","author":"Y Wang","year":"2025","unstructured":"Wang Y, Hua C, Khan AH (2025) Advances in zeroing neural networks: bio-inspired structures, performance enhancements, and applications. Biomimetics 10(5):279. https:\/\/doi.org\/10.3390\/biomimetics10050279","journal-title":"Biomimetics"},{"key":"9840_CR121","doi-asserted-by":"publisher","DOI":"10.1145\/3468507.3468517","author":"F Yang","year":"2021","unstructured":"Yang F, Liu N, Du M, Hu X (2021) Generative counterfactuals for neural networks via attribute-informed perturbation. ACM SIGKDD Explor. https:\/\/doi.org\/10.1145\/3468507.3468517","journal-title":"ACM SIGKDD Explor"},{"key":"9840_CR122","doi-asserted-by":"publisher","unstructured":"Yang Y, Kim S, Joo J (2025) Explaining deep convolutonal neural networks via latent visual-semantic filter attention, Computer vision and pattern recognition, 1\u201315. https:\/\/doi.org\/10.48550\/arXiv.2204.04601","DOI":"10.48550\/arXiv.2204.04601"},{"key":"9840_CR123","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1016\/j.ins.2023.01.012","volume":"625","author":"D You","year":"2023","unstructured":"You D, Niu S, Dong S, Yan H, Chen Z, Wu D, Shen L, Wu X (2023) Counterfactual explanation generation with minimal feature boundary. Inf Sci 625:342\u2013366. https:\/\/doi.org\/10.1016\/j.ins.2023.01.012","journal-title":"Inf Sci"},{"key":"9840_CR124","doi-asserted-by":"publisher","first-page":"5172","DOI":"10.1109\/jstars.2025.3527017","volume":"18","author":"Y Yuan","year":"2025","unstructured":"Yuan Y, Lin L, Xin Q, Zhou Z, Liu Q (2025) An empirical study on data augmentation for pixelwise satellite image time-series classification and cross-year adaptation. IEEE J Sel Top Appl Earth Obs Remote Sens 18:5172\u20135187. https:\/\/doi.org\/10.1109\/jstars.2025.3527017","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"9840_CR125","doi-asserted-by":"publisher","first-page":"135886","DOI":"10.1109\/ACCESS.2024.3461756","volume":"99","author":"Y Zeng","year":"2024","unstructured":"Zeng Y, Liao B, Li Z, Hua C, Li S (2024) Acomprehensive review of recent advances on intelligence algoeithms and information engineering applications. IEEE Access 99:135886\u2013135912. https:\/\/doi.org\/10.1109\/ACCESS.2024.3461756","journal-title":"IEEE Access"},{"key":"9840_CR127","doi-asserted-by":"publisher","unstructured":"Zhang Q, YangY, Liu Y, Wu YN, Zhu SC (2018) Unsupervised learning of neural networks to explain neural networks. Comput Vis pattern Recognit 1\u201316. https:\/\/doi.org\/10.48550\/arXiv.1805.07468","DOI":"10.48550\/arXiv.1805.07468"},{"key":"9840_CR126","doi-asserted-by":"publisher","unstructured":"Zhang R, Madumail P, Miller T, Ehinger KA, Rubinstein B, I. P (2020) Invertibale concept-based explanations for CNN models with non-negative concept activation vectors. 1\u20139. https:\/\/doi.org\/10.48550\/arXiv.2006.15417","DOI":"10.48550\/arXiv.2006.15417"},{"key":"9840_CR128","doi-asserted-by":"publisher","unstructured":"Zhao C, Ni B, Zhang J, Zhao Q, Zhang W, Tian Q, Jiao S (2019) Variational convolutional neural network pruning, in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2780\u20132789., https:\/\/doi.org\/10.1109\/CVPR.2019.00289","DOI":"10.1109\/CVPR.2019.00289"},{"issue":"9","key":"9840_CR130","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1109\/TPAMI.2018.2858759","volume":"41","author":"B Zhou","year":"2019","unstructured":"Zhou B, Bau D, Oliva A, Torralba A (2019) Interpreting deep visual representations via network dissection. IEEE Trans Pattern Anal Mach Intell 41(9):2131\u20132145. https:\/\/doi.org\/10.1109\/TPAMI.2018.2858759","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"9840_CR129","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/math13111801","volume":"13","author":"X Zhou","year":"2025","unstructured":"Zhou X, Liao B (2025) Advances in zeroing neural networks: convergence optimization and robustness in dynamic systems. Mathematics 13(11):1\u201325. https:\/\/doi.org\/10.3390\/math13111801","journal-title":"Mathematics"}],"container-title":["Evolving Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-026-09840-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12530-026-09840-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-026-09840-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T06:40:26Z","timestamp":1781678426000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12530-026-09840-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":123,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["9840"],"URL":"https:\/\/doi.org\/10.1007\/s12530-026-09840-y","relation":{},"ISSN":["1868-6478","1868-6486"],"issn-type":[{"value":"1868-6478","type":"print"},{"value":"1868-6486","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"assertion":[{"value":"28 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest regarding this publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable, as the study is a data-driven investigation using publicly available datasets from Kaggle.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"81"}}