Savo G. Glisic - Artificial Intelligence and Quantum Computing for Advanced Wireless Networks

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.