Читать книгу Artificial Intelligence and Quantum Computing for Advanced Wireless Networks - Savo G. Glisic - Страница 73

1 1 R. Caruana, Y. Lou, J. Gehrke, P. Koch, M. Sturm, and N. Elhadad, “Intelligible models for healthcare: Predicting pneumonia risk and hospital 30‐day readmission,” in Proc. 21th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2015, pp. 1721–1730.

2 2 A. Howard, C. Zhang, and E. Horvitz, “Addressing bias in machine learning algorithms: A pilot study on emotion recognition for intelligent systems,” in Proc. Adv. Robot. Social Impacts (ARSO), Mar. 2017, pp. 1–7.

3 3 (2016). European Union General Data Protection Regulation (GDPR). Accessed: Jun. 6, 2018. [Online]. Available: http://www.eugdpr.org

4 4 D. Silver, J. Schrittwieser, K. Simonyan, et al., “Mastering the game of go without human knowledge,” Nature, vol. 550, no. 7676, pp. 354–359, 2017.

5 5 M. Bojarski, D. Del Testa, D. Dworakowski, et al. (2016). “End to end learning for self‐driving cars.” [Online]. Available: https://arxiv.org/abs/1604.07316

6 6 J. Haspiel, J. Meyerson, L.P. Robert Jr, et al. (2018). Explanations and Expectations: Trust Building in Automated Vehicles, http://deepblue.lib.umich.edu. [Online]. Available: https://doi.org/10.1145/3173386.3177057

7 7 A. Holzinger, C. Biemann, C. S. Pattichis, and D. B. Kell. (2017). “What do we need to build explainable AI systems for the medical domain?” [Online]. Available: https://arxiv.org/abs/1712.09923

8 8 G. J. Katuwal and R. Chen. (2016). Machine Learning Model Interpretability for Precision Medicine. [Online]. Available: https://arxiv. org/abs/1610.09045

9 9 Z. Che, S. Purushotham, R. Khemani, and Y. Liu, “Interpretable deep models for ICU outcome prediction,” in Proc. AMIA Annu. Symp., 2017, pp. 371–380

10 10 S. Tan, R. Caruana, G. Hooker, and Y. Lou. (2018). “Detecting bias in black‐box models using transparent model distillation.” [Online]. Available: https://arxiv.org/abs/1710.06169

11 11 C. Howell, “A framework for addressing fairness in consequential machine learning,” in Proc. FAT Conf., Tuts., 2018, pp. 1–2.

12 12 Berk, R. and Bleich, J. (2013). Statistical procedures for forecasting criminal behavior: a comparative assessment. Criminol. Public Policy 12 (3): 513–544.

13 13 Equifax. (2018). Equifax Launches NeuroDecision Technology. Accessed: Jun. 6, 2018. [Online]. Available: https://investor.equifax.com news‐and‐events/news/2018/03‐26‐2018‐143044126

14 14 D. Gunning. Explainable artificial intelligence (XAI), Defense Advanced Research Projects Agency (DARPA). Accessed: Jun. 6, 2018. [Online]. Available: http://www.darpa.mil/program/explainable‐artificialintelligence

15 15 W. Knight. (2017). The U.S. military wants its autonomous machines to explain themselves, MIT Technology Review. Accessed: Jun. 6, 2018. [Online]. Available: https://www.technologyreview.com/s/603795/theus‐military‐wants‐its‐autonomous‐machines‐to‐explain‐themselves

16 16 A. Henelius, K. Puolamäki, and A. Ukkonen. (2017). “Interpreting classifiers through attribute interactions in datasets.” [Online]. Available: https://arxiv.org/abs/1707.07576

17 17 Future of Privacy Forum. (2017). Unfairness by Algorithm: Distilling the Harms of Automated Decision‐Making. Accessed: Jun. 6, 2018. [Online]. Available: https://fpf.org/wp‐content/uploads/2017/12/FPF‐AutomatedDecision‐Making‐Harms‐and‐Mitigation‐Charts.pdf

18 18 Letham, B., Rudin, C., McCormick, T.H., and Madigan, D. (2015). Interpretable classifiers using rules and Bayesian analysis: building a better stroke prediction model. Ann. Appl. Stat. 9 (3): 1350–1371.

19 19 K. Xu, J. Lei Ba, R. Kiros, et al., “Show, attend and tell: Neural image caption generation with visual attention,” in Proc. Int. Conf. Mach. Learn. (ICML), 2015, pp. 1–10

20 20 Ustun, B. and Rudin, C. (2015). Supersparse linear integer models for optimized medical scoring systems. Mach. Learn. 102 (3): 349–391.

21 21 S. Sarkar, “Accuracy and interpretability trade‐offs in machine learning applied to safer gambling,” in Proc. CEUR Workshop, 2016, pp. 79–87.

22 22 Breiman, L. (2001). Statistical modeling: the two cultures (with comments and a rejoinder by the author). Stat. Sci. 16 (3): 199–231.

23 23 Z. C. Lipton, “The mythos of model interpretability,” in Proc. ICML Workshop Hum. Interpretability Mach. Learn., 2016, pp. 96–100.

24 24 Krening, S., Harrison, B., Feigh, K.M. et al. (2016). Learning from explanations using sentiment and advice in RL. IEEE Trans. Cogn. Develop. Syst. 9 (1): 44–55.

25 25 A. Mahendran and A. Vedaldi, “Understanding deep image representations by inverting them,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 5188–5196.

26 26 T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2013, pp. 3111–3119.

27 27 G. Ras, M. van Gerven, and P. Haselager. (2018). “Explanation methods in deep learning: Users, values, concerns and challenges.” [Online]. Available: https://arxiv.org/abs/1803.07517

28 28 A. Santoro, D. Raposo, D.G.T. Barret, et al. (2017). “A simple neural network module for relational reasoning.” [Online]. Available: https://arxiv.org/abs/1706.01427

29 29 R. B. Palm, U. Paquet, and O. Winther. (2017). “Recurrent relational networks for complex relational reasoning.” [Online]. Available: https://arxiv.org/abs/1711.08028

30 30 Y. Dong, H. Su, J. Zhu, and B. Zhang, “Improving interpretability of deep neural networks with semantic information,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Mar. 2017, pp. 4306–4314.

31 31 C. Louizos, U. Shalit, J. M. Mooij, D. Sontag, R. Zemel, and M. Welling, “Causal effect inference with deep latent‐variable models,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2017, pp. 6446–6456.

32 32 O. Goudet, D. Kalainathan, P. Caillou, et al. (2017). “Learning functional causal models with generative neural networks.” [Online]. Available: https://arxiv.org/abs/1709.05321

33 33 C. Yang, A. Rangarajan, and S. Ranka. (2018). “Global model interpretation via recursive partitioning.” [Online]. Available: https://arxiv.org/abs/1802.04253

34 34 M. A. Valenzuela‐Escárcega, A. Nagesh, and M. Surdeanu. (2018). “Lightly‐supervised representation learning with global interpretability.” [Online]. Available: https://arxiv.org/abs/1805.11545

35 35 A. Nguyen, A. Dosovitskiy, J. Yosinski, T. Brox, and J. Clune, “Synthesizing the preferred inputs for neurons in neural networks via deep generator networks,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2016, pp. 3387–3395.

36 36 D. Erhan, A. Courville, and Y. Bengio, “Understanding representations learned in deep architectures,” Dept. d'Informatique Recherche Operationnelle, Univ. Montreal, Montreal, QC, Canada, Tech. Rep. 1355, 2010

37 37 M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why should I trust you?’ Explaining the predictions of any classifier,” 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2016, pp. 1135–1144

38 38 M. T. Ribeiro, S. Singh, and C. Guestrin, “Anchors: High‐precision model‐agnostic explanations,” in Proc. AAAI Conf. Artif. Intell., 2018, pp. 1–9.

39 39 J. Lei, M. G'Sell, A. Rinaldo, R. J. Tibshirani, and L. Wasserman, “Distribution‐free predictive inference for regression,” J. Amer. Stat. Assoc., to be published. [Online]. Available: http://www.stat.cmu.edu/~ryantibs/papers/conformal.pdf

40 40 Baehrens, D., Schroeter, T., Harmeling, S. et al. (2010). How to explain individual classification decisions. J. Mach. Learn. Res. 11 (6): 1803–1831.

41 41 K. Simonyan, A. Vedaldi, and A. Zisserman. (2013). “Deep inside convolutional networks: Visualising image classification models and saliency maps.” [Online]. Available: https://arxiv.org/abs/1312.6034

42 42 M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” in Proc. Eur. Conf. Comput. Vis. Zurich, Switzerland: Springer, 2014, pp. 818–833.

43 43 B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and O. Torralba, “Learning deep features for discriminative localization,” IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 2921–2929.

44 44 M. Sundararajan, A. Taly, and Q. Yan. (2017). “Axiomatic attribution for deep networks.” [Online]. Available: https://arxiv.org/abs/1703.01365

45 45 D. Smilkov, N. Thorat, B. Kim, F. Viégas, and M. Wattenberg. (2017). “SmoothGrad: Removing noise by adding noise.” [Online]. Available: https://arxiv.org/abs/1706.03825

46 46 Robnik‐Šikonja, M. and Kononenko, I. (2008). Explaining classifications for individual instances. IEEE Trans. Knowl. Data Eng. 20 (5): 589–600.

47 47 Montavon, G., Lapuschkin, S., Binder, A. et al. (2017). Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recog. 65: 211–222.

48 48 S. Bach, A. Binder, K.‐R. Müller, and W. Samek, “Controlling explanatory heatmap resolution and semantics via decomposition depth,” IEEE Int. Conf. Image Process. (ICIP), Sep. 2016, pp. 2271–2275.

49 49 R. Fong and A. Vedaldi. (2017). “Interpretable explanations of black boxes by meaningful perturbation.” [Online]. Available: https://arxiv.org/abs/1704.03296

50 50 P. Dabkowski and Y. Gal, “Real time image saliency for black box classifiers,” in Proc. Adv. Neural Inf. Process. Syst., 2017, pp. 6970–6979.

51 51 P.‐J. Kindermans, K.T. Schütt, M. Alber, et al., “Learning how to explain neural networks: PatternNet and patternAttribution,” in Proc. Int. Conf. Learn. Represent., 2018, pp. 1–16. Accessed: Jun. 6, 2018. [Online]. Available: https://openreview.net/forum?id=Hkn7CBaTW

52 52 A. Shrikumar, P. Greenside, A. Shcherbina, and A. Kundaje. (2016). “Not just a black box: Interpretable deep learning by propagating activation differences.” [Online]. Available: http://arxiv.org/abs/1605.01713

53 53 A. Ross, M. C. Hughes, and F. Doshi‐Velez, “Right for the right reasons: Training differentiable models by constraining their explanations,” in Proc. Int. Joint Conf. Artif. Intell., 2017, pp. 2662–2670.

54 54 S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” in Proc. Adv. Neural Inf. Process. Syst., 2017, pp. 4768–4777.

55 55 R. Guidotti, A. Monreale, S. Ruggieri, D. Pedreschi, F. Turini, and F. Giannotti. (2018). “Local rule‐based explanations of black box decision systems.” [Online]. Available: https://arxiv.org/abs/1805.10820

56 56 D. Linsley, D. Scheibler, S. Eberhardt, and T. Serre. (2018). “Globaland‐local attention networks for visual recognition.” [Online]. Available: https://arxiv.org/abs/1805.08819

57 57 S. Seo, J. Huang, H. Yang, and Y. Liu, “Interpretable convolutional neural networks with dual local and global attention for review rating prediction,” in Proc. 11th ACM Conf. Recommender Syst. (RecSys), 2017, pp. 297–305.

58 58 C. Molnar. (2018). Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. Accessed: Jun. 6, 2018. [Online]. Available: https://christophm.github.io/interpretable‐ml‐book

59 59 O. Bastani, C. Kim, and H. Bastani. (2017). “Interpretability via model extraction.” [Online]. Available: https://arxiv.org/abs/1706.09773

60 60 J. J. Thiagarajan, B. Kailkhura, P. Sattigeri, and K. N. Ramamurthy. (2016). “TreeView: Peeking into deep neural networks via feature‐space partitioning.” [Online]. Available: https://arxiv.org/abs/1611.07429

61 61 D. P. Green and H. L. Kern, “Modeling heterogeneous treatment effects in large‐scale experiments using Bayesian additive regression trees,” in Proc. Annu. Summer Meeting Soc. Political Methodol., 2010, pp. 1–40.

62 62 Chipman, H.A., George, E.I., and McCulloch, R.E. (2010). BART: Bayesian additive regression trees. Appl. Statist. 4 (1): 266–298.

63 63 Elith, J., Leathwick, J., and Hastie, T. (2008). A working guide to boosted regression trees. J. Anim. Ecol. 77 (4): 802–813.

64 64 S. H. Welling, H. H. F. Refsgaard, P. B. Brockhoff, and L. H. Clemmensen. (2016). “Forest floor visualizations of random forests.” [Online]. Available: https://arxiv.org/abs/1605.09196

65 65 Goldstein, A., Kapelner, A., Bleich, J., and Pitkin, E. (2015). Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J. Comput. Graph. Stat. 24 (1): 44–65. https://doi.org/10.1080/10618600.2014.907095.

66 66 G. Casalicchio, C. Molnar, and B. Bischl. (2018). “Visualizing the feature importance for black box models.” [Online]. Available: https://arxiv.org/abs/1804.06620

67 67 U. Johansson, R. König, and I. Niklasson, “The truth is in there—Rule extraction from opaque models using genetic programming,” in Proc. FLAIRS Conf., 2004, pp. 658–663.

68 68 M. H. Aung, P. Lisboa, T. Etchells, et al., “Comparing analytical decision support models through Boolean rule extraction: A case study of ovarian tumour malignancy,” in Proc. Int. Symp. Neural Netw. Berlin, Germany: Springer, 2007, pp. 1177–1186.

69 69 T. Hailesilassie. (2017). “Rule extraction algorithm for deep neural networks: A review.” [Online]. Available: https://arxiv.org/abs/1610.05267

70 70 Andrews, R., Diederich, J., and Tickle, A.B. (1995). Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl.‐Based Syst. 8 (6): 373–389.

71 71 GopiKrishna, T. (2014). Evaluation of rule extraction algorithms. Int. J. Data Mining Knowl. Manage. Process 4 (3): 9–19.

72 72 Etchells, T.A. and Lisboa, P.J.G. (Mar. 2006). Orthogonal search‐based rule extraction (OSRE) for trained neural networks: a practical and efficient approach. IEEE Trans. Neural Netw. 17 (2): 374–384.

73 73 Barakat, N. and Diederich, J. (2005). Eclectic rule‐extraction from support vector machines. Int. J. Comput. Intell. 2 (1): 59–62.

74 74 P. Sadowski, J. Collado, D. Whiteson, and P. Baldi, “Deep learning, dark knowledge, and dark matter,” in Proc. NIPS Workshop High‐Energy Phys. Mach. Learn. (PMLR), vol. 42, 2015, pp. 81–87.

75 75 G. Hinton, O. Vinyals, and J. Dean. (2015). “Distilling the knowledge in a neural network.” [Online]. Available: arXiv:1503.02531v1 [stat.ML]

76 76 Z. Che, S. Purushotham, R. Khemani, and Y. Liu. (2015). “Distilling knowledge from deep networks with applications to healthcare domain.” [Online]. Available: arXiv:1512.03542v1 [stat.ML]

77 77 K. Xu, D. H. Park, D. H. Yi, and C. Sutton. (2018). “Interpreting deep classifier by visual distillation of dark knowledge.” [Online]. Available: https://arxiv.org/abs/1803.04042

78 78 S. Tan, “Interpretable approaches to detect bias in black‐box models,” in Proc. AAAI/ACM Conf. AI Ethics Soc., 2017, pp. 1–2.

79 79 S. Tan, R. Caruana, G. Hooker, and Y. Lou. (2018). “Auditing blackbox models using transparent model distillation with side information.” [Online]. Available: arXiv:1710.06169v4 [stat.ML]

80 80 S. Tan, R. Caruana, G. Hooker, and A. Gordo. (2018). “Transparent model distillation.” [Online]. Available: https://arxiv.org/abs/1801.08640

81 81 Y. Zhang and B. Wallace. (2016). “A sensitivity analysis of (and practitioners' Guide to) convolutional neural networks for sentence classification.” [Online]. Available: https://arxiv.org/abs/1510.03820

82 82 Cortez, P. and Embrechts, M.J. (2013). Using sensitivity analysis and visualization techniques to open black box data mining models. Inform. Sci. 225: 1–17.

83 83 P. Cortez and M. J. Embrechts, “Opening black box data mining models using sensitivity analysis,” in Proc. IEEE Symp. Comput. Intell. Data Mining (CIDM), Apr. 2011, pp. 341–348.

84 84 Bach, S., Binder, A., Montavon, G. et al. (2015). On pixel‐wise explanations for non‐linear classifier decisions by layer‐wise relevance propagation. PLoS One 10 (7): e0130140.

85 85 A. Fisher, C. Rudin, and F. Dominici. (2018). “Model class reliance: Variable importance measures for any machine learning model class, from the ‘rashomon’ perspective.” [Online]. Available: https://arxiv.org/abs/1801.01489

86 86 Bien, J. and Tibshirani, R. (2011). Prototype selection for interpretable classification. Ann. Appl. Statist. 5 (4): 2403–2424.

87 87 B. Kim, C. Rudin, and J. A. Shah, “The Bayesian case model: A generative approach for case‐based reasoning and prototype classification,” in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 1952–1960.

88 88 K. S. Gurumoorthy, A. Dhurandhar, and G. Cecchi. (2017). “ProtoDash: Fast interpretable prototype selection.” [Online]. Available: https://arxiv.org/abs/1707.01212

89 89 B. Kim, R. Khanna, and O. O. Koyejo, “Examples are not enough, learn to criticize! criticism for interpretability,” in Proc. 29th Conf. Neural Inf. Process. Syst. (NIPS), 2016, pp. 2280–2288.

90 90 S. Wachter, B. Mittelstadt, and C. Russell. (2017). “Counterfactual explanations without opening the black box: Automated decisions and the GDPR.” [Online]. Available: https://arxiv.org/abs/1711.00399

91 91 X. Yuan, P. He, Q. Zhu, and X. Li. (2017). “Adversarial examples: Attacks and defenses for deep learning.” [Online]. Available: https://arxiv.org/abs/1712.07107

92 92 G. Montavon, S. Bach, A. Binder, W. Samek, and K.‐R. Muller Explaining NonLinear Classification Decisions with Deep Taylor Decomposition, arXiv:1512.02479v1 [cs.LG] 8 Dec 2015, also in Pattern Recognition, vol. 65 May 2017, Pages pp. 211–222.

93 93 W. J. Murdoch, A. Szlam, Automatic Rule Extraction from Long Short Term Memory Networks, ICLR 2017 Conference

94 94 R. Babuska, Fuzzy Systems, Modeling and Identification https://www.researchgate.net/profile/Robert_Babuska/publication/228769192_Fuzzy_Systems_Modeling_and_Identification/links/02e7e5223310e79d19000000/Fuzzy‐Systems‐Modeling‐and‐Identification.pdf

95 95 Glisic, S. (2016). Advanced Wireless Networks: Technology and Business Models. Wiley.

96 96 B. E. Boser, I. Guyon, V. N. Vapnik A training algorithm for optimal margin classifiers. In D. Haussler, editor, Proceedings of the Annual Conference on Computational Learning Theory, pages 144–152, Pittsburgh, PA, 1992. ACM Press.

97 97 Chan, W.C. et al. (2001). On the modeling of nonlinear dynamic systems using support vector neural networks. Eng. Appl. Artif. Intel. 14 (2): 105–113.

98 98 Chiang, J.H. and Hao, P.Y. (2004). Support vector learning mechanism for fuzzy rule‐based modeling: a new approach. IEEE Trans. Fuzzy Syst. 12 (1): 1–12.

99 99 Shen, J., Syau, Y., and Lee, E.S. (2007). Support vector fuzzy adaptive network in regression analysis. Comput. Math. Appl. 54 (11–12): 1353–1366.

100 100 Smola, A.J. and Schölkopf, B. (1998). The connection between regularization operators and support vector kernels. Neural Netw. 10: 1445–1454.

101 101 https://en.wikipedia.org/wiki/T‐norm:fuzzy_logics

102 102 https://en.wikipedia.org/wiki/Construction_of_t‐norms

103 103 Cherkassky, V. and Ma, Y. (2004). Practical selection of SVM parameters and noise estimation for SVM regression. Neural Netw. 17 (1): 113–126.

104 104 Chalimourda, A., Schölkopf, B., and Smola, A.J. (2004). Experimentally optimal v in support vector regression for different noise models and parameters settings. Neural Netw. 17 (1): 127–141.

105 105 Yu, L. and Xiao, J. (2009). Trade‐off between accuracy and interpretability: experience‐oriented fuzzy modeling via reduced‐set vectors. Comput. Math. Appl. 57: 885–895.