Page 170 - 《软件学报》2026年第4期

王家祺 等: 可解释深度学习的概念建模方法综述 1611

[4] Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai XH, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S,
Uszkoreit J, Houlsby N. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929, 2021.
[5] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. In: Proc. of the
31st Int’l Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 6000–6010.
[6] Zhang S, Yao LN, Sun AX, Tay Y. Deep learning based recommender system: A survey and new perspectives. ACM Computing
Surveys, 2019, 52(1): 5. [doi: 10.1145/3285029]
[7] Chib PS, Singh P. Recent advancements in end-to-end autonomous driving using deep learning: A survey. IEEE Trans. on Intelligent
Vehicles, 2024, 9(1): 103–118. [doi: 10.1109/TIV.2023.3318070]
[8] Teng QY, Liu Z, Song YQ, Han K, Lu Y. A survey on the interpretability of deep learning in medical diagnosis. Multimedia Systems,
2022, 28(6): 2335–2355. [doi: 10.1007/s00530-022-00960-4]
[9] Biswas AA. A comprehensive review of explainable AI for disease diagnosis. Array, 2024, 22: 100345. [doi: 10.1016/j.array.2024.
100345]
[10] Bussmann N, Giudici P, Marinelli D, Papenbrock J. Explainable AI in fintech risk management. Frontiers in Artificial Intelligence, 2020,
3: 26. [doi: 10.3389/frai.2020.00026]
[11] Misheva BH, Osterrieder J, Hirsa A, Kulkarni O, Lin SF. Explainable AI in credit risk management. arXiv:2103.00949, 2021.
[12] Omeiza D, Webb H, Jirotka M, Kunze L. Explanations in autonomous driving: A survey. IEEE Trans. on Intelligent Transportation
Systems, 2022, 23(8): 10142–10162. [doi: 10.1109/TITS.2021.3122865]
[13] Atakishiyev S, Salameh M, Yao HS, Goebel R. Explainable artificial intelligence for autonomous driving: A comprehensive overview
and field guide for future research directions. IEEE Access, 2024, 12: 101603–101625. [doi: 10.1109/ACCESS.2024.3431437]
[14] Chamola V, Hassija V, Sulthana AR, Ghosh D, Dhingra D, Sikdar B. A review of trustworthy and explainable artificial intelligence
(XAI). IEEE Access, 2023, 11: 78994–79015. [doi: 10.1109/ACCESS.2023.3294569]
[15] Li XH, Xiong HY, Li XJ, Wu XY, Zhang X, Liu J, Bian J, Dou DJ. Interpretable deep learning: Interpretation, interpretability,
trustworthiness, and beyond. Knowledge and Information Systems, 2022, 64(12): 3197–3234. [doi: 10.1007/s10115-022-01756-8]
[16] Islam SR, Eberle W, Ghafoor SK, Ahmed M. Explainable artificial intelligence approaches: A survey. arXiv:2101.09429, 2021.
[17] Linardatos P, Papastefanopoulos V, Kotsiantis S. Explainable AI: A review of machine learning interpretability methods. Entropy, 2020,
23(1): 18. [doi: 10.3390/e23010018]
[18] Yang PB, Sang JT, Zhang B, Feng YG, Yu J. Survey on interpretability of deep models for image classification. Ruan Jian Xue
Bao/Journal of Software, 2023, 34(1): 230–254 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6415.htm [doi: 10.
13328/j.cnki.jos.006415]
[19] Montavon G, Samek W, Müller KR. Methods for interpreting and understanding deep neural networks. Digital Signal Processing, 2018,
73: 1–15. [doi: 10.1016/j.dsp.2017.10.011]
[20] Zurada JM, Malinowski A, Cloete I. Sensitivity analysis for minimization of input data dimension for feedforward neural network. In:
Proc. of the 1994 IEEE Int’l Symp. on Circuits and Systems. London: IEEE, 1994. 447–450. [doi: 10.1109/ISCAS.1994.409622]
[21] Montavon G, Binder A, Lapuschkin S, Samek W, Müller KR. Layer-wise relevance propagation: An overview. In: Explainable AI:
Interpreting, Explaining and Visualizing Deep Learning. Cham: Springer, 2019. 193–209. [doi: 10.1007/978-3-030-28954-6_10]
[22] Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual explanations from deep networks via gradient-
based localization. In: Proc. of the 2017 IEEE Int’l Conf. on Computer Vision. Venice: IEEE, 2017. 618–626. [doi: 10.1109/ICCV.2017.74]
[23] Kim B, Wattenberg M, Gilmer J, Cai C, Wexler J, Viegas F, Sayres R. Interpretability beyond feature attribution: Quantitative testing
with concept activation vectors (TCAV). In: Proc. of the 35th Int’l Conf. on Machine Learning. Stockholm: PMLR, 2018. 2668–2677.
[24] Chen CF, Li O, Tao CF, Barnett AJ, Su JK, Rudin C. This looks like that: Deep learning for interpretable image recognition. In: Proc. of
the 33rd Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2019. 8930–8941.
[25] Yang Q, Fan LX, Zhu J, Chen YX, Zhang QS, Zhu SC, Tao DC, Cui P, Zhou SH, Liu Q, Huang XQ, Zhang YF. Introduction to
Explainable Artificial Intelligence. Beijing: Electronics Industry Press, 2022 (in Chinese).
[26] Margolis E. A reassessment of the shift from the classical theory of concepts to prototype theory. Cognition, 1994, 51(1): 73–89. [doi: 10.
1016/0010-0277(94)90009-4]
[27] Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. In: Proc. of the 13th European Conf. on Computer Vision
(ECCV 2014). Zurich: Springer, 2014. 818–833. [doi: 10.1007/978-3-319-10590-1_53]
[28] Molnar C. Interpretable Machine Learning. Lulu.com, 2020.
[29] Crabbé J, van der Schaar M. Concept activation regions: A generalized framework for concept-based explanations. In: Proc. of the 36th
Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates Inc., 2022. 2590–2607.