Advertisement

Towards Explainable AI Using Similarity: An Analogues Visualization System

  • Vinícius SeguraEmail author
  • Bruna Brandão
  • Ana Fucs
  • Emilio Vital Brazil
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11584)

Abstract

AI Systems are becoming ubiquitous and assuming different roles in our lives: they can act as recommendation systems in multiple contexts, they can work as personal assistants, they can tag images, etc. Whilst their contributions are clear, the reasoning behind them are not so transparent and may need explanations. This need for interpretability created new challenges for developers and designers from different communities. Visualizing multidimensional data and exploring the objects’ similarities can help with the explainability of an AI system. In this work, we discuss the visual inspection of high-dimensional objects being complementary to machine learning techniques. We present RAVA (Reservoir Analogues Visual Analytics), a system that employs machine learning and visual analytics techniques to empower geoscientists in the task of finding similar reservoirs.

Keywords

Visualization Similarity Analogues AI systems 

References

  1. 1.
    Ankerst, M., Berchtold, S., Keim, D.A.: Similarity clustering of dimensions for an enhanced visualization of multidimensional data. In: Proceedings of the IEEE Symposium on Information Visualization, pp. 52–60. IEEE (1998)Google Scholar
  2. 2.
    Brazil, E.V., Segura, V., Cerqueira, R., de Paula, R., Mello, U.: Visual analytics for reservoir analogues. In: ACE 2018 Annual Convention & Exhibition (2018)Google Scholar
  3. 3.
    Fuchs, J., Isenberg, P., Bezerianos, A., Fischer, F., Bertini, E.: The influence of contour on similarity perception of star glyphs. IEEE Trans. Visual Comput. Graphics 20(12), 2251–2260 (2014)CrossRefGoogle Scholar
  4. 4.
    Henley, M., Hagen, M., Bergeron, R.D.: Evaluating two visualization techniques for genome comparison. In: 11th International Conference on Information Visualization, IV 2007, pp. 551–558. IEEE (2007)Google Scholar
  5. 5.
    Key, A., Howe, B., Perry, D., Aragon, C.: VizDeck: self-organizing dashboards for visual analytics. In: Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data, SIGMOD 2012, pp. 681–684. ACM, New York (2012)Google Scholar
  6. 6.
    Latecki, L.J., Lakamper, R.: Shape similarity measure based on correspondence of visual parts. IEEE Trans. Pattern Anal. Mach. Intell. 22(10), 1185–1190 (2000)CrossRefGoogle Scholar
  7. 7.
    Lipton, Z.C.: The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016)
  8. 8.
    Lipton, Z.C.: The doctor just won’t accept that! (2017)Google Scholar
  9. 9.
    Medin, D.L., Goldstone, R.L., Gentner, D.: Respects for similarity. Psychol. Rev. 100(2), 254–278 (1993)CrossRefGoogle Scholar
  10. 10.
    Pandey, A.V., Krause, J., Felix, C., Boy, J., Bertini, E.: Towards understanding human similarity perception in the analysis of large sets of scatter plots. In: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pp. 3659–3669. ACM (2016)Google Scholar
  11. 11.
    e Silva, R.D.G., et al.: Sensitivity analysis in a machine learning methodology for reservoir analogues. In: Rio Oil & Gas 2018, vol. 1 (2018)Google Scholar
  12. 12.
    Yang, J., Peng, W., Ward, M.O., Rundensteiner, E.A.: Interactive hierarchical dimension ordering, spacing and filtering for exploration of high dimensional datasets. In: IEEE Symposium on Information Visualization, INFOVIS 2003, pp. 105–112. IEEE (2003)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.IBM ResearchRio de JaneiroBrazil
  2. 2.University of CalgaryCalgaryCanada

Personalised recommendations