Abstract
Deep learning (DL) is an excellent function estimator which has amazing result on perception tasks such as visualization recognition and text recognition. But, its inner architecture acts as a black box, because the users cannot understand why such decisions are made. Bayesian reasoning (BR) provides explanation facility and causal reasoning in terms of uncertainty which is able to overcome demerit of DL. This paper is to propose a framework for the integration of DL and BR by leveraging their complementary merits based on their inherent internal architecture. The migration from deep neural network (DNN) to Bayesian network (BN) involves extracting rules from DNN and constructing an efficient BN based on the rules generated, to provide intelligent decision support with accurate recommendations and logical explanations to the users.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kim, B.: Interactive and interpretable machine learning models for human machine collaboration. Doctoral dissertation, Massachusetts Institute of Technology (2015)
Lipton, Z. C.: The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016)
Castelvecchi, D.: Can we open the black box of AI? Nat. News 538(7623), 20 (2016)
Ping, C. W.: A methodology for constructing causal knowledge model from fuzzy cognitive map to bayesian belief network. Unpublished Ph.D. Thesis, Chonnam National University (2009)
Cheah, W.P., Kim, Y.S., Kim, K.Y., Yang, H.J.: Systematic causal knowledge acquisition using FCM constructor for product design decision support. Expert Syst. Appl. 38(12), 15316–15331 (2011)
Wee, Y.Y., Cheah, W.P., Tan, S.C., Wee, K.: A method for root cause analysis with a Bayesian belief network and fuzzy cognitive map. Expert Syst. Appl. 42(1), 468–487 (2015)
Zilke, J.: Extracting rules from deep neural networks. Unpublished thesis (2015)
Zarikas, V., Papageorgiou, E., Regner, P.: Bayesian network construction using a fuzzy rule based approach for medical decision support. Expert Syst. 32(3), 344–369 (2015)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Bengio, Y.: Learning deep architectures for AI. Found. Trends® Mach. Learn. 2(1), 1–127 (2009)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)
Markoff, J.: Scientists see promise in deep-learning programs. New York Times, 23 (2012)
Deng, L.: Computational models for speech production. In: Ponting, K. (ed.) Computational Models of Speech Pattern Processing, pp. 199–213. Springer, Berlin, Heidelberg (1999). https://doi.org/10.1007/978-3-642-60087-6_20
Deng, L.: Switching dynamic system models for speech articulation and acoustics. In: Johnson, M., Khudanpur, S.P., Ostendorf, M., Rosenfeld, R. (eds.) Mathematical Foundations of Speech and Language Processing, pp. 115–133. Springer, New York (2004). https://doi.org/10.1007/978-1-4419-9017-4_6
George, D.: How the brain might work: a hierarchical and temporal model for learning and recognition. Stanford University, Palo Alto, California (2008)
Bouvrie, J.V.: Hierarchical learning: theory with applications in speech and vision. Doctoral dissertation, Massachusetts Institute of Technology (2009)
Pearl, J.: Causality: Models, Reasoning and Inference, vol. 29. MIT Press, Cambridge (2000)
Kleinberg, S.: Why: A Guide to Finding and Using Causes. O’Reilly Media Inc, Sebastopol (2015)
Kleinberg, S.: Causality, Probability, and Time. Cambridge University Press, Cambridge (2013)
Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017)
Bojarski, M., et al.: Explaining how a deep neural network trained with end-to-end learning steers a car. arXiv preprint arXiv:1704.07911 (2017)
Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., Elhadad, N.: Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1721–1730. ACM, August 2015
Holzinger, A., Biemann, C., Pattichis, C.S., Kell, D.B.: What do we need to build explainable AI systems for the medical domain? arXiv preprint arXiv:1712.09923 (2017)
Goodman, B., Flaxman, S.: European Union regulations on algorithmic decision-making and a “right to explanation”. AI Mag. 38(3), 50–57 (2017)
Ehsan, U., Harrison, B., Chan, L., Riedl, M.O.: Rationalization: a neural machine translation approach to generating natural language explanations. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pp. 81–87. ACM, December 2018
Wang, H., Yeung, D.Y.: Towards Bayesian deep learning: a framework and some existing methods. IEEE Trans. Knowl. Data Eng. 28(12), 3395–3408 (2016)
Brendel, W., Bethge, M.: Approximating CNNs with bag-of-local-features models works surprisingly well on imagenet. arXiv preprint arXiv:1904.00760 (2019)
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, August 2016
Samek, W., Wiegand, T., Müller, K.R.: Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:1708.08296 (2017)
Tamagnini, P., Krause, J., Dasgupta, A., Bertini, E.: Interpreting black-box classifiers using instance-level visual explanations. In: Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics, p. 6. ACM, May 2017
Burns, C., Thomason, J., Tansey, W.: Interpreting Black Box Models with Statistical Guarantees. arXiv preprint arXiv:1904.00045 (2019)
Bastani, O., Kim, C., Bastani, H.: Interpreting blackbox models via model extraction. arXiv preprint arXiv:1705.08504 (2017)
Shwartz-Ziv, R., Tishby, N.: Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810 (2017)
Gunning, D.: Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA), nd Web, 2 (2017)
Gunning, D., Aha, D.W.: DARPA’s explainable artificial intelligence program. AI Mag. 40(2), 44–58 (2019)
Hailesilassie, T.: Rule extraction algorithm for deep neural networks: a review. arXiv preprint arXiv:1610.05267 (2016)
González, C., Loza Mencía, E., Fürnkranz, J.: Re-training deep neural networks to facilitate Boolean concept extraction. In: Yamamoto, A., Kida, T., Uno, T., Kuboyama, T. (eds.) DS 2017. LNCS (LNAI), vol. 10558, pp. 127–143. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67786-6_10
Acknowledgments
This work was supported by the Fundamental Research Grant Scheme (FRGS) from the Ministry of Education and Multimedia University, Malaysia (Project ID: FRGS/1/2018/ICT02/MMU/02/1).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tan, S.Y., Cheah, W.P., Tan, S.C. (2019). Integrating Deep Learning and Bayesian Reasoning. In: Wang, G., Bhuiyan, M.Z.A., De Capitani di Vimercati, S., Ren, Y. (eds) Dependability in Sensor, Cloud, and Big Data Systems and Applications. DependSys 2019. Communications in Computer and Information Science, vol 1123. Springer, Singapore. https://doi.org/10.1007/978-981-15-1304-6_10
Download citation
DOI: https://doi.org/10.1007/978-981-15-1304-6_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1303-9
Online ISBN: 978-981-15-1304-6
eBook Packages: Computer ScienceComputer Science (R0)