Abstract
Within the realm of deep learning, the interpretability of Convolutional Neural Networks (CNNs), particularly in the context of image classification tasks, remains a formidable challenge. To this end, we present a neurosymbolic framework, NeSyFOLD-G that generates a symbolic rule-set using the last layer kernels of the CNN to make its underlying knowledge interpretable. We find groups of similar kernels in the CNN (kernel-grouping) using the cosine-similarity score between the feature maps generated by various kernels. Once such kernel groups are found, we binarize each kernel group’s output and use it to generate a rule-set using a Rule Based Machine Learning (RBML) algorithm called FOLD-SE-M. We present a novel kernel grouping algorithm and show that grouping similar kernels leads to a significant reduction in the size of the rule-set generated by FOLD-SE-M, consequently, improving the interpretability. The rule-set can be viewed as a stratified Answer Set Program wherein each predicate’s truth value depends on a kernel group in the CNN. Each predicate in the rule-set is mapped to a semantic concept using a novel semantic labeling algorithm that utilizes a few semantic segmentation masks of the images used for training. The last layers of the CNN can then be replaced by this rule-set to obtain the NeSy-G model which can then be used for the image classification task. The goal-directed ASP system s(CASP) can be used to obtain the justification of any prediction made using the NeSy-G model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arias, J., Carro, M., Salazar, E., Marple, K., Gupta, G.: Constraint answer set programming without grounding. Theory Pract. Logic Program. 18(3–4), 337–354 (2018)
Bologna, G., Fossati, S.: A two-step rule-extraction technique for a CNN. Electronics 9(6), 990 (2020)
Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: Advances in Neural Information Processing Systems 32 (2019)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Denil, M., Demiraj, A., de Freitas, N.: Extraction of salient sentences from labelled documents (2014). https://doi.org/10.48550/ARXIV.1412.6815. https://arxiv.org/abs/1412.6815
Evans, R., Grefenstette, E.: Learning explanatory rules from noisy data. J. Artif. Intell. Res. 61, 1–64 (2018)
Ferreira, J., de Sousa Ribeiro, M., Gonçalves, R., Leite, J.: Looking inside the black-box: logic-based explanations for neural networks. In: Proceedings of the 19th International Conference on Principles of Knowledge Representation and Reasoning, pp. 432–442, August 2022. https://doi.org/10.24963/kr.2022/45
Gelfond, M., Kahl, Y.: Knowledge Representation, Reasoning, and the Design of Intelligent Agents: The Answer-Set Programming Approach. Cambridge University Press, Cambridge (2014)
Kanagaraj, N., Hicks, D., Goyal, A., Mishra Tiwari, S., Singh, G.: Deep learning using computer vision in self driving cars for lane and traffic sign detection. Int. J. Syst. Assur. Eng. Manag. 12, May 2021. https://doi.org/10.1007/s13198-021-01127-6
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). https://doi.org/10.48550/ARXIV.1412.6980. https://arxiv.org/abs/1412.6980
Kirillov, A., et al.: Segment anything (2023)
Ko, B., Kwak, S.: Survey of computer vision-based natural disaster warning systems. Opt. Eng. 51, 0901 (2012). https://doi.org/10.1117/1.OE.51.7.070901
Lage, I., et al.: Human evaluation of models built for interpretability. In: Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, vol. 7, pp. 59–67 (2019)
Law, M., Russo, A., Broda, K.: The ILASP system for inductive learning of answer set programs. arXiv:2005.00904 (2020)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989). https://doi.org/10.1162/neco.1989.1.4.541
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Muggleton, S.: Inductive logic programming. New Gen. Comput. 8(4), 295–318 (1991)
Padalkar, P., Wang, H., Gupta, G.: NeSyFOLD: neurosymbolic framework for interpretable image classification (2023). https://arxiv.org/abs/2301.12667
Qi, Z., Khorram, S., Fuxin, L.: Embedding deep networks into visual explanations. Artif. Intell. 292, 103435 (2021). https://doi.org/10.1016/j.artint.2020.103435
Ray, O.: Nonmonotonic abductive inductive learning. J. Appl. Logic 7(3), 329–340 (2009). https://doi.org/10.1016/j.jal.2008.10.007. https://www.sciencedirect.com/science/article/pii/S1570868308000682. Special Issue: Abduction and Induction in Artificial Intelligence
Reiter, R.: A logic for default reasoning. Artif. Intell. 13(1), 81–132 (1980). https://doi.org/10.1016/0004-3702(80)90014-4. https://www.sciencedirect.com/science/article/pii/0004370280900144. Special Issue on Non-Monotonic Logic
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Sen, P., de Carvalho, B.W., Riegel, R., Gray, A.: Neuro-symbolic inductive logic programming with logical neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 8212–8219 (2022)
Shindo, H., Nishino, M., Yamamoto, A.: Differentiable inductive logic programming for structured examples. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 5034–5041 (2021)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps (2013). https://doi.org/10.48550/ARXIV.1312.6034. https://arxiv.org/abs/1312.6034
Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323–332 (2012). https://doi.org/10.1016/j.neunet.2012.02.016. https://www.sciencedirect.com/science/article/pii/S0893608012000457. Selected Papers from IJCNN 2011
Sun, W., Zheng, B., Qian, W.: Computer aided lung cancer diagnosis with deep learning algorithms. In: SPIE Medical Imaging (2016)
Townsend, J., Kasioumis, T., Inakoshi, H.: ERIC: extracting relations inferred from convolutions. In: Ishikawa, H., Liu, C.L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNIP, vol. 12624, pp. 206–222. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-69535-4_13
Townsend, J., Kudla, M., Raszkowska, A., Kasiousmis, T.: On the explainability of convolutional layers for multi-class problems. In: Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations (2022). https://openreview.net/forum?id=jgVpiERy8Q8
Wang, H., Gupta, G.: FOLD-SE: an efficient rule-based machine learning algorithm with scalable explainability (2022). https://doi.org/10.48550/ARXIV.2208.07912
Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., Huang, T.: SegGPT: towards segmenting everything in context. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1130–1140 (2023)
Xie, N., Sarker, M.K., Doran, D., Hitzler, P., Raymer, M.: Relating input concepts to convolutional neural network decisions (2017). https://doi.org/10.48550/ARXIV.1711.08006
Yang, Y., Kim, S., Joo, J.: Explaining deep convolutional neural networks via latent visual-semantic filter attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8333–8343 (2022)
Yang, Z., Ishay, A., Lee, J.: NeurASP: embracing neural networks into answer set programming. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020 (2021)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhang, Q., Cao, R., Shi, F., Wu, Y.N., Zhu, S.C.: Interpreting CNN knowledge via an explanatory graph. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Zhang, Q., Cao, R., Wu, Y.N., Zhu, S.C.: Growing interpretable part graphs on convnets via multi-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452–1464 (2017)
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5122–5130 (2017). https://doi.org/10.1109/CVPR.2017.544
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Padalkar, P., Wang, H., Gupta, G. (2023). Using Logic Programming and Kernel-Grouping for Improving Interpretability of Convolutional Neural Networks. In: Gebser, M., Sergey, I. (eds) Practical Aspects of Declarative Languages. PADL 2024. Lecture Notes in Computer Science, vol 14512. Springer, Cham. https://doi.org/10.1007/978-3-031-52038-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-52038-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-52037-2
Online ISBN: 978-3-031-52038-9
eBook Packages: Computer ScienceComputer Science (R0)