Constrained Image Generation Using Binarized Neural Networks with Decision Procedures

  • Svyatoslav Korneev
  • Nina NarodytskaEmail author
  • Luca Pulina
  • Armando Tacchella
  • Nikolaj Bjorner
  • Mooly Sagiv
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10929)


We consider the problem of binary image generation with given properties. This problem arises in a number of practical applications, including generation of artificial porous medium for an electrode of lithium-ion batteries, for composed materials, etc. A generated image represents a porous medium and, as such, it is subject to two sets of constraints: topological constraints on the structure and process constraints on the physical process over this structure. To perform image generation we need to define a mapping from a porous medium to its physical process parameters. For a given geometry of a porous medium, this mapping can be done by solving a partial differential equation (PDE). However, embedding a PDE solver into the search procedure is computationally expensive. We use a binarized neural network to approximate a PDE solver. This allows us to encode the entire problem as a logical formula. Our main contribution is that, for the first time, we show that this problem can be tackled using decision procedures. Our experiments show that our model is able to produce random constrained images that satisfy both topological and process constraints.


  1. 1.
    Arunachalam, H., Korneev, S., Battiato, I., Onori, S.: Multiscale modeling approach to determine effective lithium-ion transport properties. In: 2017 American Control Conference (ACC), pp. 92–97, May 2017Google Scholar
  2. 2.
    Battiato, I., Tartakovsky, D.: Applicability regimes for macroscopic models of reactive transport in porous media. J. Contam. Hydrol. 120–121, 18–26 (2011)CrossRefGoogle Scholar
  3. 3.
    Hermann, H., Elsner, A.: Geometric models for isotropic random porous media: a review. Adv. Mater. Sci. Eng. 2014 (2014)CrossRefGoogle Scholar
  4. 4.
    Pyrcz, M., Deutsch, C.: Geostatistical reservoir modeling (2014)Google Scholar
  5. 5.
    Hornung, U. (ed.): Homogenization and Porous Media. Interdisciplinary Applied Mathematics, vol. 6. Springer, New York (1997). Scholar
  6. 6.
    Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C., Bengio, Y.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 8–13 December 2014, Montreal, Quebec, Canada, pp. 2672–2680 (2014)Google Scholar
  7. 7.
    Goodfellow, I.J.: NIPS 2016 tutorial: generative adversarial networks. CoRR abs/1701.00160 (2017)Google Scholar
  8. 8.
    Osokin, A., Chessel, A., Salas, R.E.C., Vaggi, F.: GANs for biological image synthesis. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2252–2261, October 2017Google Scholar
  9. 9.
    Korneev, S.: Using convolutional neural network to calculate effective properties of porous electrode.
  10. 10.
    Arunachalam, H., Korneev, S., Battiato, I.: Using convolutional neural network to calculate effective properties of porous electrode. J. Electrochem. Soc. (2018, in preparation to submit)Google Scholar
  11. 11.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. CoRR abs/1511.06434 (2015)Google Scholar
  12. 12.
    Chintala, S.: How to train a GAN? Tips and tricks to make GANs work.
  13. 13.
    Luke de Oliveira, M.P., Nachman, B.: Tips and tricks for training GANs with physics constraints. In: Workshop at the 31st Conference on Neural Information Processing Systems (NIPS), Deep Learning for Physical Sciences, December 2017Google Scholar
  14. 14.
    Narodytska, N., Kasiviswanathan, S.P., Ryzhyk, L., Sagiv, M., Walsh, T.: Verifying properties of binarized deep neural networks. CoRR abs/1709.06662 (2017)Google Scholar
  15. 15.
    Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Lee, D.D., Sugiyama, M., Luxburg, U.V., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29, pp. 4107–4115. Curran Associates Inc., Red Hook (2016)Google Scholar
  16. 16.
    Cheng, C., Nührenberg, G., Ruess, H.: Verification of binarized neural networks. CoRR abs/1710.03107 (2017)Google Scholar
  17. 17.
    Katz, G., Barrett, C., Dill, D., Julian, K., Kochenderfer, M.: Reluplex: an efficient SMT solver for verifying deep neural networks. arXiv preprint arXiv:1702.01135 (2017)
  18. 18.
    Cheng, C.-H., Nührenberg, G., Ruess, H.: Maximum resilience of artificial neural networks. In: D’Souza, D., Narayan Kumar, K. (eds.) ATVA 2017. LNCS, vol. 10482, pp. 251–268. Springer, Cham (2017). Scholar
  19. 19.
    Huang, X., Kwiatkowska, M., Wang, S., Wu, M.: Safety verification of deep neural networks. In: Majumdar, R., Kunčak, V. (eds.) CAV 2017. LNCS, vol. 10426, pp. 3–29. Springer, Cham (2017). Scholar
  20. 20.
    Dao, T., Duong, K., Vrain, C.: Constrained clustering by constraint programming. Artif. Intell. 244, 70–94 (2017)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Ganji, M., Bailey, J., Stuckey, P.J.: A declarative approach to constrained community detection. In: Beck, J.C. (ed.) CP 2017. LNCS, vol. 10416, pp. 477–494. Springer, Cham (2017). Scholar
  22. 22.
    Guns, T., Dries, A., Nijssen, S., Tack, G., Raedt, L.D.: Miningzinc: a declarative framework for constraint-based mining. Artif. Intell. 244, 6–29 (2017)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Luke de Oliveira, M.P., Nachman, B.: Generative adversarial networks for simulation. In: 18th International Workshop on Advanced Computing and Analysis Techniques in Physics Research, August 2017Google Scholar
  24. 24.
    Hu, Y., Gibson, E., Lee, L.-L., Xie, W., Barratt, D.C., Vercauteren, T., Noble, J.A.: Freehand ultrasound image simulation with spatially-conditioned generative adversarial networks. In: Cardoso, M.J., et al. (eds.) CMMI/SWITCH/RAMBO -2017. LNCS, vol. 10555, pp. 105–115. Springer, Cham (2017). Scholar
  25. 25.
    Ravanbakhsh, S., Lanusse, F., Mandelbaum, R., Schneider, J.G., Póczos, B.: Enabling dark energy science with deep generative models of galaxy images. In: Singh, S.P., Markovitch, S. (eds.) Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 4–9 February 2017, San Francisco, California, USA, pp. 1488–1494. AAAI Press (2017)Google Scholar
  26. 26.
    Deng, L., Jiao, P., Pei, J., Wu, Z., Li, G.: Gated XNOR networks: deep neural networks with ternary weights and activations under a unified discretization framework. CoRR abs/1705.09283 (2017)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Svyatoslav Korneev
    • 1
  • Nina Narodytska
    • 2
    Email author
  • Luca Pulina
    • 3
  • Armando Tacchella
    • 4
  • Nikolaj Bjorner
    • 5
  • Mooly Sagiv
    • 2
    • 6
  1. 1.Department of Energy Resources EngineeringStanfordUSA
  2. 2.VMware ResearchPalo AltoUSA
  3. 3.Chemistry and Pharmacy DepartmentUniversity of SassariSassariItaly
  4. 4.DIBRISUniversity of GenoaGenoaItaly
  5. 5.Microsoft ResearchRedmondUSA
  6. 6.Tel Aviv UniversityTel AvivIsrael

Personalised recommendations