Abstract
Our main contribution is to show that the behaviour of kernels across multiple layers of a convolutional neural network can be approximated using a logic program. The extracted logic programs yield accuracies that correlate with those of the original model, though with some information loss in particular as approximations of multiple layers are chained together or as lower layers are quantised. We also show that an extracted program can be used as a framework for further understanding the behaviour of CNNs. Specifically, it can be used to identify key kernels worthy of deeper inspection and also identify relationships with other kernels in the form of the logical rules. Finally, we make a preliminary, qualitative assessment of rules we extract from the last convolutional layer and show that kernels identified are symbolic in that they react strongly to sets of similar images that effectively divide output classes into sub-classes with distinct characteristics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Preliminary experiments found that l1 norm yielded higher fidelity than l2 norm.
- 2.
Limited space made it difficult to show all 10 without compromising clarity.
References
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you?: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144. ACM (2016)
Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., Kagal, L.: Explaining explanations: an overview of interpretability of machine learning. In: 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), pp. 80–89. IEEE (2018)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51, 93 (2018)
Andrews, R., Diederich, J., Tickle, A.B.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl.-Based Syst. 8, 373–389 (1995)
Jacobsson, H.: Rule extraction from recurrent neural networks: a taxonomy and review. Neural Comput. 17, 1223–1263 (2005)
Townsend, J., Chaton, T., Monteiro, J.M.: Extracting relational explanations from deep neural networks: a survey from a neural-symbolic perspective. IEEE Trans. Neural Networks Learn. Syst. 31, 3456 (2019)
Zhang, Q., Zhu, S.: Visual interpretability for deep learning: a survey. Front. Inf. Technol. Electron. Eng. 19, 27–39 (2018)
Lamb, L., Garcez, A., Gori, M., Prates, M., Avelar, P., Vardi, M.: Graph neural networks meet neural-symbolic computing: a survey and perspective. arXiv preprint arXiv:2003.00330 (2020)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
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
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)
Bojarski, M., et al.: Visualbackprop: efficient visualization of CNNs. arXiv preprint arXiv:1611.05418 (2016)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One 10, e0130140 (2015)
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., Müller, K.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Networks Learn. Syst. 28, 2660–2673 (2017)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. arXiv preprint arXiv:1704.02685 (2017)
Frosst, N., Hinton, G.: Distilling a neural network into a soft decision tree. arXiv preprint arXiv:1711.09784 (2017)
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, pp. 8930–8941 (2019)
Bologna, G., Fossati, S.: A two-step rule-extraction technique for a CNN. Electronics 9, 990 (2020)
Zhang, Q., Cao, R., Wu, Y.N., Zhu, S.: Growing interpretable part graphs on convnets via multi-shot learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Zhang, Q., Cao, R., Shi, F., Wu, Y.N., Zhu, S.: Interpreting CNN knowledge via an explanatory graph. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Zhang, Q., Yang, Y., Ma, H., Wu, Y.N.: Interpreting CNNs via decision trees. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6261–6270 (2019)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. arXiv preprint arXiv:1412.6856 (2014)
Zhang, Q., Nian Wu, Y., Zhu, S.: Interpretable convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8827–8836 (2018)
Percy, C., d’Avila Garcez, A.S., Dragicevic, S., França, M.V., Slabaugh, G.G., Weyde, T.: The need for knowledge extraction: understanding harmful gambling behavior with neural networks. Front. Artif. Intell. Appl. 285, 974–981 (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: High-precision model-agnostic explanations. In: AAAI Conference on Artificial Intelligence (2018)
Zilke, J.R., Loza Mencía, E., Janssen, F.: DeepRED – rule extraction from deep neural networks. In: Calders, T., Ceci, M., Malerba, D. (eds.) DS 2016. LNCS (LNAI), vol. 9956, pp. 457–473. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46307-0_29
Schaaf, N., Huber, M.F.: Enhancing decision tree based interpretation of deep neural networks through l1-orthogonal regularization. arXiv preprint arXiv:1904.05394 (2019)
Nguyen, T.D., Kasmarik, K.E., Abbass, H.A.: Towards interpretable deep neural networks: an exact transformation to multi-class multivariate decision trees. arXiv preprint arXiv:2003.04675 (2020)
Murdoch, W.J., Szlam, A.: Automatic rule extraction from long short term memory networks. arXiv preprint arXiv:1702.02540 (2017)
Tran, S.N., d’Avila Garcez, A.S.: Deep logic networks: inserting and extracting knowledge from deep belief networks. IEEE Trans. Neural Networks Learn. Syst. 29, 246 (2016)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929. IEEE (2016)
Denil, M., Demiraj, A., De Freitas, N.: Extraction of salient sentences from labelled documents. arXiv preprint arXiv:1412.6815 (2014)
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)
Simon, M., Rodner, E., Denzler, J.: Part detector discovery in deep convolutional neural networks. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9004, pp. 162–177. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16808-1_12
Xie, N., Sarker, M.K., Doran, D., Hitzler, P., Raymer, M.: Relating input concepts to convolutional neural network decisions. arXiv preprint arXiv:1711.08006 (2017)
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, 1452 (2017)
Quinlan, J.R.: C4.5: programming for machine learning. The Morgan Kaufmann Series in Machine Learning, pp. 38–48. Morgan Kaufmann, San Mateo, CA (1993)
Chollet, F., et al.: Keras (2015). https://github.com/fchollet/keras
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Townsend, J., Kasioumis, T., Inakoshi, H. (2021). ERIC: Extracting Relations Inferred from Convolutions. In: Ishikawa, H., Liu, CL., Pajdla, T., Shi, J. (eds) Computer Vision – ACCV 2020. ACCV 2020. Lecture Notes in Computer Science(), vol 12624. Springer, Cham. https://doi.org/10.1007/978-3-030-69535-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-69535-4_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69534-7
Online ISBN: 978-3-030-69535-4
eBook Packages: Computer ScienceComputer Science (R0)