Explaining nonlinear classification decisions with deep Taylor decomposition

Pattern Recognition

Volumn 65, Issue , 2017, Pages 211-222

  Montavon, Grégoire ^a   Lapuschkin, Sebastian ^b   Binder, Alexander ^c   Samek, Wojciech ^b   Müller, Klaus Robert ^a,d  

^a TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

^b FRAUNHOFER HEINRICH HERTZ INSTITUTE   (Germany)

^c SINGAPORE UNIVERSITY OF TECHNOLOGY AND DESIGN   (Singapore)

^d Korea University   (South Korea)

Author keywords

Deep neural networks; Heatmapping; Image recognition; Relevance propagation; Taylor decomposition

Indexed keywords

IMAGE RECOGNITION; LEARNING SYSTEMS; MULTILAYERS; NETWORK ARCHITECTURE;

DEEP NEURAL NETWORKS; HEATMAPPING; MACHINE LEARNING PROBLEM; NETWORK CLASSIFICATION; NON-LINEAR METHODS; NONLINEAR CLASSIFICATION; NONLINEAR STRUCTURE; SCOPE OF APPLICATION;

MULTILAYER NEURAL NETWORKS;

EID: 85010676902     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patcog.2016.11.008     Document Type: Article

References (52)

1. [1] Jordan, M.I., Learning in Graphical Models. 1998, MIT Press, Cambridge, MA, USA.
2. [2] Schölkopf, B., Smola, A.J., Learning with Kernels Support Vector Machines, Regularization, Optimization, and Beyond. 2002, MIT Press, Cambridge, MA, USA.
3. [3] Müller, K.-R., Mika, S., Rätsch, G., Tsuda, K., Schölkopf, B., An introduction to kernel-based learning algorithms. IEEE Trans. Neural Netw. 12:2 (2001), 181–201.
4. [4] Rasmussen, C.E., Williams, C.K.I., Gaussian Processes for Machine Learning. 2006, MIT Press, Cambridge, MA, USA.
5. [5] Bishop, C.M., Neural Networks for Pattern Recognition. 1995, Oxford University Press, Inc., New York, NY, USA.
6. [6] G. Montavon, G.B. Orr, K.-R. Müller (eds.), Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, vol. 7700. Springer, Berlin Heidelberg, 2012.
7. [7] Y. LeCun, L. Bottou, G.B. Orr, K.-R. Müller, Efficient backprop, in: Neural Networks: Tricks of the Trade, 2nd ed., Springer, Berlin Heidelberg, 2012, pp. 9–48.
8. [8] Schapire, R.E., Freund, Y., Boosting. 2012, MIT Press, Cambridge, MA, USA.
9. [9] Breiman, L., Random forests. Mach. Learn. 45:1 (2001), 5–32.
10. [10] A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, vol. 25, 2012, pp. 1106–1114.
11. [11] D.C. Ciresan, A. Giusti, L.M. Gambardella, J. Schmidhuber, Deep neural networks segment neuronal membranes in electron microscopy images, in: Advances in Neural Information Processing Systems, vol. 25, 2012, pp. 2852–2860.
12. [12] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S.E. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7–12, 2015, 2015, pp. 1–9.
13. [13] Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.P., Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12 (2011), 2493–2537.
14. [14] R. Socher, A. Perelygin, J. Wu, J. Chuang, C.D. Manning, A. Ng, C. Potts, Recursive deep models for semantic compositionality over a sentiment treebank, in: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, October 2013, pp. 1631–1642.
15. [15] S. Ji, W. Xu, M. Yang, K. Yu, 3d convolutional neural networks for human action recognition, in: Proceedings of the 27th International Conference on Machine Learning (ICML-10), June 21–24, 2010, Haifa, Israel, 2010, pp. 495–502.
16. [16] Q.V. Le, W.Y. Zou, S.Y. Yeung, A.Y. Ng, Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis, in: The 24th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3361–3368, 2011.
17. [17] Ijjina, E.P., Chalavadi, K.M., Human action recognition using genetic algorithms and convolutional neural networks. Pattern Recognit., 2016.
18. [18] Montavon, G., Rupp, M., Gobre, V., Vazquez-Mayagoitia, A., Hansen, K., Tkatchenko, A., Müller, K.-R., von Lilienfeld, O.A., Machine learning of molecular electronic properties in chemical compound space. New J. Phys., 15(9), 2013, 095003.
19. [19] Baldi, P., Sadowski, P., Whiteson, D., Searching for exotic particles in high-energy physics with deep learning. Nat. Commun., 5(4308), 2014.
20. [20] Haufe, S., Meinecke, F.C., Görgen, K., Dähne, S., Haynes, J., Blankertz, B., Bießmann, F., On the interpretation of weight vectors of linear models in multivariate neuroimaging. NeuroImage 87 (2014), 96–110.
21. [21] Oaxaca, R., Male-female wage differentials in urban labor markets. Int. Econ. Rev. 14:3 (1973), 693–709.
22. [22] B. Poulin, R. Eisner, D. Szafron, P. Lu, R. Greiner, D.S. Wishart, A. Fyshe, B. Pearcy, C. Macdonell, J. Anvik, Visual explanation of evidence with additive classifiers, in: Proceedings, The Twenty-First National Conference on Artificial Intelligence and the Eighteenth Innovative Applications of Artificial Intelligence Conference, 2006, pp. 1822–1829.
23. [23] Simonyan, K., Vedaldi, A., Zisserman, A., Deep inside convolutional networks: visualising image classification models and saliency maps. CoRR, 2013 vol. abs/1312.6034.
24. [24] M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional networks, in: Computer Vision – ECCV 2014 – 13th European Conference, 2014, pp. 818–833.
25. [25] Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., Samek, W., On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One, 10(7), 2015, e0130140.
26. [26] Rumelhart, D., Hinton, G., Williams, R., Learning representations by back-propagating errors. Nature 323:6088 (1986), 533–536.
27. [27] Samek, W., Binder, A., Montavon, G., Lapuschkin, S., Müller, K.-R., Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst. 99 (2016), 1–14.
28. [28] Braun, M.L., Buhmann, J.M., Müller, K.-R., On relevant dimensions in kernel feature spaces. J. Mach. Learn. Res. 9 (2008), 1875–1908.
29. [29] Montavon, G., Braun, M.L., Krueger, T., Müller, K.-R., Analyzing local structure in kernel-based learning: explanation, complexity, and reliability assessment. IEEE Signal Process. Mag. 30:4 (2013), 62–74.
30. [30] Montavon, G., Braun, M.L., Müller, K.-R., Kernel analysis of deep networks. J. Mach. Learn. Res. 12 (2011), 2563–2581.
31. [31] I.J. Goodfellow, Q.V. Le, A.M. Saxe, H. Lee, A.Y. Ng, Measuring invariances in deep networks, in: Advances in Neural Information Processing Systems, vol. 22, pp. 646–654, 2009.
32. [32] D. Erhan, A. Courville, Y. Bengio, Understanding Representations Learned in Deep Architectures, Technical Report 1355, University of Montreal, 2010.
33. [33] Krishnan, R., Sivakumar, G., Bhattacharya, P., Extracting decision trees from trained neural networks. Pattern Recognit. 32:12 (1999), 1999–2009.
34. [34] Krishnan, R., Sivakumar, G., Bhattacharya, P., A search technique for rule extraction from trained neural networks. Pattern Recognit. Lett. 20:3 (1999), 273–280.
35. [35] Baehrens, D., Schroeter, T., Harmeling, S., Kawanabe, M., Hansen, K., Müller, K.-R., How to explain individual classification decisions. J. Mach. Learn. Res. 11 (2010), 1803–1831.
36. [36] W. Landecker, M.D. Thomure, L.M.A. Bettencourt, M. Mitchell, G.T. Kenyon, S.P. Brumby, Interpreting individual classifications of hierarchical networks, in: IEEE Symposium on Computational Intelligence and Data Mining, 2013, pp. 32–38.
37. [37] Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I.J., Fergus, R., Intriguing properties of neural networks. CoRR, 2013 vol. abs/1312.6199.
38. [38] S. Bazen, X. Joutard, The Taylor decomposition: a unified generalization of the Oaxaca method to nonlinear models, Technical Report 2013-32, Aix-Marseille University, 2013.
39. [39] H. Fang, S. Gupta, F.N. Iandola, R.K. Srivastava, L. Deng, P. Dollár, J. Gao, X. He, M. Mitchell, J.C. Platt, C.L. Zitnick, G. Zweig, From captions to visual concepts and back, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7–12, 2015, 2015, pp. 1473–1482.
40. [40] H. Larochelle, G.E. Hinton, Learning to combine foveal glimpses with a third-order Boltzmann machine, in: Advances in Neural Information Processing Systems 23, 2010, pp. 1243–1251.
41. [41] K. Xu, J. Ba, R. Kiros, K. Cho, A.C. Courville, R. Salakhutdinov, R.S. Zemel, Y. Bengio, Show, attend and tell: Neural image caption generation with visual attention, in: Proceedings of the 32nd International Conference on Machine Learning, 2015, pp. 2048–2057.
42. [42] L. Arras, F. Horn, G. Montavon, K.-R. Müller, W. Samek, Explaining predictions of non-linear classifiers in NLP, in: Proceedings of the Workshop on Representation Learning for NLP at Association for Computational Linguistics (ACL), 2016.
43. [43] Sturm, I., Lapuschkin, S., Samek, W., Müller, K.-R., Interpretable deep neural networks for single-trial EEG classification. J. Neurosci. Methods 274 (2016), 141–145.
44. [44] Gevrey, M., Dimopoulos, I., Lek, S., Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol. Model. 160:3 (2003), 249–264.
45. [45] Moosavi-Dezfooli, S., Fawzi, A., Frossard, P., Deepfool: a simple and accurate method to fool deep neural networks. CoRR, 2015 vol. abs/1511.04599.
46. [46] Garson, D.G., Interpreting neural-network connection weights. AI Expert 6:4 (1991), 46–51.
47. [47] Y. LeCun, Generalization and network design strategies, in: Connectionism in Perspective, Elsevier, Zurich, Switzerland, 1989.
48. [48] Y. Jia, Caffe: an open source convolutional architecture for fast feature embedding, 2016, 〈 http://caffe.berkeleyvision.org〉.
49. [49] J. Deng, A. Berg, S. Satheesh, H. Su, A. Khosla, F.-F. Li, The ImageNet Large Scale Visual Recognition Challenge 2012 (ILSVRC2012) 〈 http://www.image-net.org/challenges/LSVRC/2012〉.
50. [50] Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Li, F., Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115:3 (2015), 211–252.
51. [51] Yu, W., Yang, K., Bai, Y., Yao, H., Rui, Y., Visualizing and comparing convolutional neural networks. CoRR, 2014 vol. abs/1412.6631.
52. [52] S. Lapuschkin, A. Binder, G. Montavon, K.-R. Müller, W. Samek, Analyzing classifiers: Fisher vectors and deep neural networks, in: IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2912–2920.