nach oben

Erschienen in:

2023 | OriginalPaper | Buchkapitel

On Explanations for Hybrid Artificial Intelligence

verfasst von : Lars Nolle, Frederic Stahl, Tarek El-Mihoub

Erschienen in: Artificial Intelligence XL

Verlag: Springer Nature Switzerland

Einloggen

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

search-config

KI-gestützte Suche

Aus

Abstract

The recent developments of machine learning (ML) approaches within artificial intelligence (AI) systems often require explainability of ML models. In order to establish trust in these systems, for example in safety critical applications, a number of different explainable artificial intelligence (XAI) methods have been proposed, either post-hoc or intrinsic models. These can help to understand why a ML model has made a particular decision. The authors of this paper point out that the abbreviation XAI is commonly used in the literature referring to explainable ML models, although the term AI encompasses many more topics than ML. To improve efficiency and effectiveness of AI, two or more AI subsystems are often combined to solve a common problem. In this case, an overall explanation has to be derived from the subsystems’ explanations. In this paper we define the term hybrid AI. This is followed by reviewing the current state of XAI before proposing the use of blackboard systems (BBS) to not only share results but also to integrate and to exchange explanations of different XAI models as well, in order to derive an overall explanation for hybrid AI systems.

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

Nächstes Kapitel Intermediate Task Ensembling for Sarcasm Detection

Maedche, A., et al.: AI-based digital assistants: opportunities, threats, and research perspectives. Bus. Inf. Syst. Eng. 61, 535–544 (2019). https://doi.org/10.1007/s12599-019-00600-8CrossRef

Gao, X., Bian, X.: Autonomous driving of vehicles based on artificial intelligence. J. Intell. Fuzzy Syst. 41, 1–10 (2021). https://doi.org/10.3233/JIFS-189982CrossRef

EC. Artificial Intelligence for Europe, European Commission, COM (2018) 237. European Commission (2018)

Jordan, M.I., Mitchell, T.M.: Machine learning: trends, perspectives, and prospects. Science 349, 255–260 (2015). https://doi.org/10.1126/science.aaa8415MathSciNetCrossRefMATH

Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Net. 61, 85–117 (2014). https://doi.org/10.1016/j.neunet.2014.09.003CrossRef

Li, Y., et al.: A deep learning-based hybrid framework for object detection and recognition in autonomous driving. IEEE Access 8, 194228–194239 (2020). https://doi.org/10.1109/ACCESS.2020.3033289CrossRef

Hernandez, C.S., Ayo, S., Panagiotakopoulos, D.: An explainable artificial intelligence (xAI) framework for improving trust in automated ATM tools. In: 2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC), pp. 1–10 (2021). https://doi.org/10.1109/DASC52595.2021.9594341

Wang, Y., Chung, S.: Artificial intelligence in safety-critical systems: a systematic review. Ind. Manag. Data Syst. 122(2), 442–470 (2021). https://doi.org/10.1108/IMDS-07-2021-0419CrossRef

Zhou, J., Gandomi, A.H., Chen, F., Holzinger, A.: Evaluating the quality of machine learning explanations: a survey on methods and metrics. Electronics 10, 593 (2021). https://doi.org/10.3390/electronics10050593CrossRef

10.

EASA. Artificial intelligence roadmap: a human-centric approach to AI aviation. European Union Aviation Safety Agency (2020)

11.

Kersting, K.: Rethinking computer science through AI. KI - Künstliche Intelligenz 34(4), 435–437 (2020). https://doi.org/10.1007/s13218-020-00692-5CrossRef

12.

Nolle, L., Wong, K.C.P., Hopgood, A.A.: DARBS: a distributed blackboard system. In: Bramer, M., Coenen, F., Preece, A. (eds.) Research and Development in Intelligent Systems XVIII, pp. 161–170. Springer, London (2002). https://doi.org/10.1007/978-1-4471-0119-2_13CrossRef

13.

Bielecki, A., Wójcik, M.: Hybrid AI system based on ART neural network and Mixture of Gaussians modules with application to intelligent monitoring of the wind turbine. Appl. Soft Comput. 108, 107400 (2021). https://doi.org/10.1016/j.asoc.2021.107400CrossRef

14.

Tachmazidis, I., Chen, T., Adamou, M., Antoniou, G.: A hybrid AI approach for supporting clinical diagnosis of attention deficit hyperactivity disorder (ADHD) in adults. Health Inf. Sci. Syst. 9, 1 (2021). https://doi.org/10.1007/s13755-020-00123-7CrossRef

15.

Li, M., et al.: A decision support system using hybrid AI based on multi-image quality model and its application in color design. Future Gener. Comput. Syst. 113, 70–77 (2020). https://doi.org/10.1016/j.future.2020.06.034CrossRef

16.

Zheng, N., et al.: Predicting COVID-19 in China using hybrid AI model. IEEE Trans. Cybern. 50, 2891–2904 (2020). https://doi.org/10.1109/TCYB.2020.2990162CrossRef

17.

El-Mihoub, T., Hopgood, A.A., Nolle, L., Battersby, A.: Hybrid genetic algorithms – a review. Eng. Lett. 13(2), 124–137 (2006). ISSN: 1816-093X

18.

Althoff, D., Bazame, H.C., Nascimento, J.G.: Untangling hybrid hydrological models with explainable artificial intelligence. H2Open J. 4, 13–28 (2021). https://doi.org/10.2166/h2oj.2021.066

19.

Akata, Z., et al.: A research agenda for hybrid intelligence: augmenting human intellect with collaborative, adaptive, responsible, and explainable artificial intelligence. Computer 53, 18–28 (2020). https://doi.org/10.1109/MC.2020.2996587CrossRef

20.

Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., Zhong, C.: Interpretable machine learning: fundamental principles and 10 grand challenges. arXiv (2021). https://doi.org/10.48550/ARXIV.2103.11251

21.

Kim, M.-Y., et al.: A multi-component framework for the analysis and design of explainable artificial intelligence. Mach. Learn. Knowl. Extract. 3, 900–921 (2021). https://doi.org/10.3390/make3040045CrossRef

22.

Buhrmester, V., Münch, D., Arens, M.: Analysis of explainers of black box deep neural networks for computer vision: a survey. Mach. Learn. Knowl. Extract. 3, 966–989 (2021)CrossRef

23.

Li, X.-H., et al.: A survey of data-driven and knowledge-aware eXplainable AI. IEEE Trans. Knowl. Data Eng. 34(1), 29–49 (2020)MathSciNet

24.

Gunning, D., Vorm, E., Wang, J.Y., Turek, M.: DARPA’s explainable AI (XAI) program: a retrospective. Appl. AI Lett. (2021)

25.

Liao, Q.V., Varshney, K.R.: Human-centered explainable AI (XAI): from algorithms to user experiences, CoRR, Bd. abs/2110.10790 (2021)

26.

El-Mihoub, T.A., Nolle, L., Stahl, F.: Explainable boosting machines for network intrusion detection with features reduction. In: Bramer, M., Stahl, F. (eds.) Artificial Intelligence XXXIX: 42nd SGAI International Conference on Artificial Intelligence, AI 2022, Cambridge, UK, December 13–15, 2022, Proceedings, pp. 280–294. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-21441-7_20CrossRef

27.

Gunning, D., Aha, D.: DARPA’s explainable artificial intelligence (XAI) program. AI Mag. 40(2), 44–58 (2019)

28.

Nori, H., Jenkins, S., Koch, P., Caruana, R.: InterpretML: a unified framework for machine learning interpretability. arXiv (2019)

29.

Hastie, T., Tibshirani, R.: Generalized additive models: some applications. J. Am. Stat. Assoc. 82(398), 371–386 (1987)CrossRefMATH

30.

Arik, S.O., Pfister, T.: TabNet: attentive interpretable tabular learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 6679–6687 (2021). https://ojs.aaai.org/index.php/AAAI/article/view/16826

31.

Park, D.H., et al.: Multimodal explanations: justifying decisions and pointing to the evidence. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018)

32.

Li, O., Liu, H., Chen, C., Rudin, C.: Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: The Thirty-Second AAAI Conference, pp. 3530–3537 (2018)

33.

Lei, T., Barzilay, R., Jaakkola, T.: Rationalizing neural predictions. arXiv (2016). https://doi.org/10.48550/ARXIV.1606.04155

34.

Jiang, J., Kahai, S., Yang, M.: Who needs explanation and when? Juggling explainable AI and user epistemic uncertainty. Int. J. Hum. Comput. Stud. 165, 102839 (2022)CrossRef

35.

Craven, M.W., Shavlik, J.W.: Extracting tree-structured representations of trained networks. In: Proceedings of the 8th International Conference on Neural Information Processing Systems, Denver, Colorado, pp. 24–30 (1995)

36.

Zhou, Z.-H., Jiang, Y., Chen, S.-F.: Extracting symbolic rules from trained neural network ensembles. AI Commun. 16(1), 3–15 (2003)MATH

37.

Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv (2015). https://doi.org/10.48550/ARXIV.1503.02531

38.

Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: Explaining the predictions of any classifier. In: The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, USA (2016)

39.

Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3449–3457 (2017). https://doi.org/10.1109/ICCV.2017.371

40.

Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: The 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA, pp. 4768–4777 (2017)

41.

Friedman, J.F.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001)MathSciNetCrossRefMATH

42.

Apley, D.W., Zhu, J.: Visualizing the effects of predictor variables in black box supervised learning models. arXiv (2016). https://doi.org/10.48550/ARXIV.1612.08468

43.

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

44.

Karimi, A.-H., Barthe, G., Balle, B., Valera, I.: Model-agnostic counterfactual explanations for consequential decisions. In: Chiappa, S., Calandra, R. (ed.) Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, vol. 108, pp. 895–905. PMLR (2020). https://proceedings.mlr.press/v108/karimi20a.html

45.

Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: FAT* 2020, Barcelona, Spain (2020)

46.

Liu, S., Kailkhura, B., Loveland, D., Han, Y.: Generative counterfactual introspection for explainable deep learning. In: 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) (2019)

47.

Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618–626 (2017). https://doi.org/10.1109/ICCV.2017.74

48.

Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning, Sydney, vol. 70, pp. 3319–3328. JMLR.org (2017)

49.

Malan, K.M.: A survey of advances in landscape analysis for optimisation. Algorithms 14(2), 40 (2021)MathSciNetCrossRef

50.

Michalak, K.: Low-dimensional euclidean embedding for visualization of search spaces in combinatorial optimization. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, New York, NY, USA (2019)

51.

De Lorenzo, A., Medvet, E., Tušar, T., Bartoli, A.: An analysis of dimensionality reduction techniques for visualizing evolution. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, New York, NY, USA (2019)

52.

Ochoa, G., Malan, K.M., Blum, C.: Search trajectory networks: a tool for analysing and visualising the behaviour of metaheuristics. Appl. Soft Comput. 109, 107492 (2021)CrossRef

53.

Serafini, L., et al.: On some foundational aspects of human-centered artificial intelligence. arXiv preprint arXiv:2112.14480 (2021)

54.

Weitz, K., Schiller, D., Schlagowski, R., Huber, T., André, E.: “Let me explain!”: exploring the potential of virtual agents in explainable AI interaction design. J. Multimodal User Interfaces 15(2), 87–98 (2021). https://doi.org/10.1007/s12193-020-00332-0CrossRef

55.

Kokorakis, V.M., Petridis, M., Kapetanakis, S.: A blackboard based hybrid multi-agent system for improving classification accuracy using reinforcement learning techniques. In: Bramer, M., Petridis, M. (eds.) SGAI 2017. LNCS (LNAI), vol. 10630, pp. 47–57. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71078-5_4CrossRef

56.

Golding, D., Chesnokov, A.M.: Features of informational control complex of autonomous spacecraft. In: IFAC Workshop Aerospace Guidance, Navigation and Flight Control Systems. International Federation of Automatic Control, Laxenburg (2011)

57.

Misztal-Radecka, J., Indurkhya, B.: A blackboard system for generating poetry. Comput. Sci. 17(2), 265–294 (2016)CrossRef

58.

He, L., Li, G., Xing, L., Chen, Y.: An autonomous multi-sensor satellite system based on multi-agent blackboard model. Maintenance Reliab. 19(3), 447–458 (2017)CrossRef

59.

Stewart, R., Palmer, T.S., Bays, S.: Toward an agent-based blackboard system for reactor design optimization. Nucl. Technol. 208(5), 822–842 (2021). https://doi.org/10.1080/00295450.2021.1960783CrossRef

60.

Xu, J.S., Smith, T.J.: Massive data storage and sharing algorithm in distributed heterogeneous environment. J. Intell. Fuzzy Syst. 35(4), 4017–4026 (2018)CrossRef

61.

Straub, J.: Automating maintenance for a one-way transmitting blackboard system used for autonomous multi-tier control. Expert. Syst. 33(6), 518–530 (2016)CrossRef

62.

Engelmore, R.S., Morgan, A.J.: Blackboard Systems. Addison-Wesley (1988)

63.

McManus, J.W.: A concurrent distributed system for aircraft tactical decision generation. In: IEEE/AtAA/NASA 9th Digital Avionics Systems Conference, New York, USA, pp. 161–170 (1990)

64.

Naaman, M., Zaks, A.: Fractal blackboard systems. In: Proceedings of the 8th Israeli Conference on Computer-Based Systems and Software Engineering, pp 23–29 (1997)

65.

Stahl, F., Bramer, M.: Computationally efficient induction of classification rules with the PMCRI and J-PMCRI frameworks. Knowl.-Based Syst. 35, 49–63 (2012)CrossRef

66.

Stahl, F., Ferdinand, O., Nolle, L., Pehlken, A., Zielinski, O.: AI enabled bio waste contamination-scanner. In: Bramer, M., Ellis, R. (eds.) Artificial Intelligence XXXVIII: 41st SGAI International Conference on Artificial Intelligence, AI 2021, Cambridge, UK, December 14–16, 2021, Proceedings, pp. 357–363. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-91100-3_28CrossRef

67.

Gruber, T.R.: A translation approach to portable ontology specifications. Knowl. Acquis. 5, 199–220 (1993)CrossRef

68.

Panigutti, C., Perotti, A., Pedreschi, D.: Doctor XAI: an ontology-based approach to black-box sequential data classification explanations, pp. 629–639. Association for Computing Machinery, New York (2020)

69.

Chari, S., Seneviratne, O., Gruen, D.M., Foreman, M.A., Das, A.K., McGuinness, D.L.: Explanation ontology: a model of explanations for user-centered AI. In: Pan, J.Z., et al. (eds.) ISWC 2020. LNCS, vol. 12507, pp. 228–243. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-62466-8_15CrossRef

Titel: On Explanations for Hybrid Artificial Intelligence
verfasst von: Lars Nolle
Frederic Stahl
Tarek El-Mihoub
Verlag: Springer Nature Switzerland
Buch: Artificial Intelligence XL
Print ISBN: 978-3-031-47993-9

Electronic ISBN: 978-3-031-47994-6

Copyright-Jahr: 2023
DOI: https://doi.org/10.1007/978-3-031-47994-6_1

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"

Premium Partner