nach oben

Erschienen in:

2021 | OriginalPaper | Buchkapitel

A General Approach to Compute the Relevance of Middle-Level Input Features

verfasst von : Andrea Apicella, Salvatore Giugliano, Francesco Isgrò, Roberto Prevete

Erschienen in: Pattern Recognition. ICPR International Workshops and Challenges

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

This work proposes a novel general framework, in the context of eXplainable Artificial Intelligence (XAI), to construct explanations for the behaviour of Machine Learning (ML) models in terms of middle-level features which represent perceptually salient input parts. One can isolate two different ways to provide explanations in the context of XAI: low and middle-level explanations. Middle-level explanations have been introduced for alleviating some deficiencies of low-level explanations such as, in the context of image classification, the fact that human users are left with a significant interpretive burden: starting from low-level explanations, one has to identify properties of the overall input that are perceptually salient for the human visual system. However, a general approach to correctly evaluate the elements of middle-level explanations with respect ML model responses has never been proposed in the literature.

We experimentally evaluate the proposed approach to explain the decisions made by an Imagenet pre-trained VGG16 model on STL-10 images and by a customised model trained on the JAFFE dataset, using two different computational definitions of middle-level features and compare it with two different XAI middle-level methods. The results show that our approach can be used successfully in different computational definitions of middle-level explanations.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Deep Learning for Astrophysics, Understanding the Impact of Attention on Variability Induced by Parameter Initialization

Nächstes Kapitel Evaluation of Interpretable Association Rule Mining Methods on Time-Series in the Maritime Domain

Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018)CrossRef

Apicella, A., Isgro, F., Prevete, R., Sorrentino, A., Tamburrini, G.: Explaining classification systems using sparse dictionaries. In: Proceedings of the ESANN, Special Session on Societal Issues in Machine Learning: When Learning from Data is Not Enough. Bruges, Belgium (2019)

Apicella, A., Isgrò, F., Prevete, R., Tamburrini, G.: Contrastive explanations to classification systems using sparse dictionaries. In: Ricci, E., Rota Bulò, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) ICIAP 2019, Part I. LNCS, vol. 11751, pp. 207–218. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30642-7_19CrossRef

Apicella, A., Isgrò, F., Prevete, R., Tamburrini, G.: Middle-level features for the explanation of classification systems by sparse dictionary methods. Int. J. Neural Syst. 30(08), 2050040 (2020)CrossRef

Apicella, A., Isgro, F., Prevete, R., Tamburrini, G., Vietri, A.: Sparse dictionaries for the explanation of classification systems. In: PIE, p. 009. Rome, Italy (2019)

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), e0130140 (2015)CrossRef

Barghout, L.: Spatial-taxon information granules as used in iterative fuzzy-decision-making for image segmentation. In: Pedrycz, W., Chen, S.-M. (eds.) Granular Computing and Decision-Making. SBD, vol. 10, pp. 285–318. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16829-6_12CrossRef

Caccavale, R., Finzi, A.: Learning attentional regulations for structured tasks execution in robotic cognitive control. Auton. Robot. 43(8), 2229–2243 (2019). https://doi.org/10.1007/s10514-019-09876-xCrossRef

Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215–223 (2011)

10.

Craven, M., Shavlik, J.W.: Extracting tree-structured representations of trained networks. In: Advances in Neural Information Processing Systems, pp. 24–30. Denver, CO, USA (1996)

11.

Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding (2018)

12.

Erhan, D., Bengio, Y., Courville, A., Vincent, P.: Visualizing higher-layer features of a deep network. Univ. Montreal 1341(3), 1 (2009)

13.

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, Turin, Italy (2018)

14.

Guidotti, R., Monreale, A., Ruggieri, S., Pedreschi, D., Turini, F., Giannotti, F.: Local rule-based explanations of black box decision systems. CoRR abs/1805.10820 (2018)

15.

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(5), 93 (2018)

16.

Jenatton, R., Obozinski, G., Bach, F.: Structured sparse principal component analysis. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 366–373 (2010)

17.

Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: Advances in Neural Information Processing Systems, pp. 556–562 (2001)

18.

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

19.

Li, X.H., et al.: A survey of data-driven and knowledge-aware explainable AI. IEEE Trans. Knowl. Data Eng. (2020). https://doi.org/10.1109/TKDE.2020.2983930

20.

Lyons, M., Akamatsu, S., Kamachi, M., Gyoba, J.: Coding facial expressions with Gabor wavelets. In: Proceedings, Third IEEE International Conference on Automatic Face and Gesture Recognition, pp. 200–205. IEEE Computer Society (1998)

21.

Montavon, G., Samek, W., Müller, K.: Methods for interpreting and understanding deep neural networks. Digit. Signal Process. 73, 1–15 (2018)MathSciNetCrossRef

22.

Nguyen, A., Dosovitskiy, A., Yosinski, J., Brox, T., Clune, J.: Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 3387–3395. Curran Associates, Inc. (2016)

23.

Nguyen, A., Yosinski, J., Clune, J.: Understanding neural networks via feature visualization: a survey. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.-R. (eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700, pp. 55–76. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28954-6_4CrossRef

24.

Oh, S.J., Schiele, B., Fritz, M.: Towards reverse-engineering black-box neural networks. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.-R. (eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700, pp. 121–144. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28954-6_7CrossRef

25.

Reyes, O., Ventura, S.: Performing multi-target regression via a parameter sharing-based deep network. Int. J. Neural Syst. 29, 1950014 (2019)CrossRef

26.

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. KDD ’16, ACM (2016)

27.

Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: High-precision model-agnostic explanations. In: Thirty-Second AAAI Conference on Artificial Intelligence. New Orleans, Louisiana, USA (2018)

28.

Richter, C., Vega-Brown, W., Roy, N.: Bayesian learning for safe high-speed navigation in unknown environments. In: Bicchi, A., Burgard, W. (eds.) Robotics Research. SPAR, vol. 3, pp. 325–341. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-60916-4_19CrossRef

29.

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. 28(11), 2660–2673 (2016)MathSciNetCrossRef

30.

Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)

31.

Springenberg, J., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. In: Proceedings of the International Conference on Learning Representation (Workshop Track). San Diego, CA (2015)

32.

Tessitore, G., Prevete, R.: Designing structured sparse dictionaries for sparse representation modeling. In: Burduk, R., Kurzynski, M., Wozniak, M., Zolnierek, A. (eds.) Computer Recognition Systems 4. Advances in Intelligent and Soft Computing, vol. 95, pp. 157–166. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-20320-6_17CrossRef

33.

Vedaldi, A., Soatto, S.: Quick shift and kernel methods for mode seeking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 705–718. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88693-8_52CrossRef

34.

Zhang, Q., Zhu, S.: Visual interpretability for deep learning: a survey. Front. Inf. Technol. Electron. Eng. 19(1), 27–39 (2018). https://doi.org/10.1631/FITEE.1700808CrossRef

Titel: A General Approach to Compute the Relevance of Middle-Level Input Features
verfasst von: Andrea Apicella
Salvatore Giugliano
Francesco Isgrò
Roberto Prevete
Verlag: Springer International Publishing
Buch: Pattern Recognition. ICPR International Workshops and Challenges
Print ISBN: 978-3-030-68795-3

Electronic ISBN: 978-3-030-68796-0

Copyright-Jahr: 2021
DOI: https://doi.org/10.1007/978-3-030-68796-0_14

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"