Skip to main content

Hopfield Networks for Vector Quantization

  • 1386 Accesses

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 12397)

Abstract

We consider the problem of finding representative prototypes within a set of data and solve it using Hopfield networks. Our key idea is to minimize the mean discrepancy between kernel density estimates of the distributions of data points and prototypes. We show that this objective can be cast as a quadratic unconstrained binary optimization problem which is equivalent to a Hopfield energy minimization problem. This result is of current interest as it suggests that vector quantization can be accomplished via adiabatic quantum computing.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-61616-8_16
  • Chapter length: 12 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   119.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-61616-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   159.99
Price excludes VAT (USA)
Fig. 1.

References

  1. Amari, S.I.: Neural theory of association and concept-formation. Biol. Cybern. 26(3), 175–185 (1977). https://doi.org/10.1007/BF00365229

    CrossRef  MATH  Google Scholar 

  2. Arbel, M., Binkowski, M., Sutherland, D., Gretton, A.: On gradient regularizers for MMD GANs. In: Proceeding NeurIPS (2019)

    Google Scholar 

  3. Bauckhage, C., Brito, E., Cvejoski, K., Ojeda, C., Sifa, R., Wrobel, S.: Ising models for binary clustering via adiabatic quantum computing. In: Pelillo, M., Hancock, E. (eds.) EMMCVPR 2017. LNCS, vol. 10746, pp. 3–17. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78199-0_1

    CrossRef  Google Scholar 

  4. Bauckhage, C., Sanchez, R., Sifa, R.: Problem solving with hopfield networks and adiabatic quantum computing. In: Proceedings IJCNN (2020)

    Google Scholar 

  5. Bauckhage, C., Sifa, R., Dong, T.: Prototypes within minimum enclosing balls. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11731, pp. 365–376. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30493-5_36

    CrossRef  Google Scholar 

  6. Bauckhage, C., Thurau, C.: Adapting information theoretic clustering to binary images. In: Proceedings ICPR (2010)

    Google Scholar 

  7. Bian, Z., Chudak, F., Macready, W., Rose, G.: The Ising Model: Teaching an Old Problem New Tricks. Technical report, D-Wave Systems (2010)

    Google Scholar 

  8. Binkowski, M., Sutherland, D., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: Proceedings ICLR (2018)

    Google Scholar 

  9. Caro, M., Aarva, A., Deringer, V., Csanyi, G., Laurila, T.: Reactivity of amorphous carbon surfaces: rationalizing the role of structural motifs in functionalization using machine learning. Chem. Mater. 30(21), 7446–7455 (2018). https://doi.org/10.1021/acs.chemmater.8b03353

    CrossRef  Google Scholar 

  10. Cheng, Y.: Mean shift, mode seeking, and clustering. IEEE Trans. Pattern Anal. Mach. Intell. 17(8), 767–776 (1995). https://doi.org/10.1109/34.400568

    CrossRef  Google Scholar 

  11. Dasgupta, S., Freund, Y.: Random projection trees for vector quantization. IEEE Trans. Inf. Theory 55(7), 3229–3242 (2009). https://doi.org/10.1109/TIT.2009.2021326

    MathSciNet  CrossRef  MATH  Google Scholar 

  12. Ding, C.: Data clustering: principal components, hopfield and self-aggregation networks. In: Proceedings IJCAI (2003)

    Google Scholar 

  13. Drachen, A., Sifa, R., Thurau, C.: The name in the game: patterns in character names and game tags. Entertain. Comput. 5(1), 21–32 (2014). https://doi.org/10.1016/j.entcom.2014.02.001

    CrossRef  Google Scholar 

  14. Dziugaite, G., Roy, D., Ghahramani, Z.: Training generative neural networks via maximum mean discrepancy optimization. In: Proceedings UAI (2015)

    Google Scholar 

  15. Fukunaga, K., Hostelter, L.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory 21(1), 32–40 (1975). https://doi.org/10.1109/TIT.1975.1055330

    MathSciNet  CrossRef  Google Scholar 

  16. Gersho, A., Gray, R.: Vector Quantization and Signal Compression. Springer, Heidelberg (1991)

    MATH  Google Scholar 

  17. Gretton, A., Borgwardt, K., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(25), 723–773 (2012)

    MathSciNet  MATH  Google Scholar 

  18. Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Prentice Hall (2008)

    Google Scholar 

  19. Hopfield, J.: Neural networks and physical systems with collective computational abilities. PNAS 79(8), 2554–2558 (1982). https://doi.org/10.1073/pnas.79.8.2554

    MathSciNet  CrossRef  MATH  Google Scholar 

  20. Jegelka, S., Gretton, A., Schölkopf, B., Sriperumbudur, B.K., von Luxburg, U.: Generalized clustering via kernel embeddings. In: Mertsching, B., Hund, M., Aziz, Z. (eds.) KI 2009. LNCS (LNAI), vol. 5803, pp. 144–152. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04617-9_19

    CrossRef  Google Scholar 

  21. Johnson, M., et al.: Quantum annealing with manufactured spins. Nature 473(7346), 194–198 (2011). https://doi.org/10.1038/nature10012

    CrossRef  Google Scholar 

  22. Kohonen, T.: Learning vector quantization. In: Self-Organizing Maps. Springer Series in Information Sciences, vol. 30, pp. 175–189. Springer, Heidelberg (1995). https://doi.org/10.1007/978-3-642-97610-0_6

  23. Lehn-Schioler, T., Hedge, A., Erdogmus, D., Principe, J.: Vector quantization using information theoretic concepts. Nat. Comput. 4(1), 39–51 (2005). https://doi.org/10.1007/s11047-004-9619-8

    MathSciNet  CrossRef  MATH  Google Scholar 

  24. Li, C.L., Chang, W.C., Cheng, Y., Tang, Y., Poczos, B.: MMD GAN: towards Deeper understanding of moment matching network. In: Proceedings NIPS (2017)

    Google Scholar 

  25. Li, Y., Swersky, K., Zemel, R.: Generative moment matching networks. In: Proceedings ICML (2015)

    Google Scholar 

  26. Linde, Y., Buzo, A., Gray, R.: An algorithm for vector quantizer design. IEEE Trans. Commun. 28(1), 84–95 (1980). https://doi.org/10.1109/TCOM.1980.1094577

    CrossRef  Google Scholar 

  27. Lucas, A.: Ising formulations of many NP problems. Front. Phys. 2, 5:1–5:15 (2014). https://doi.org/10.3389/fphy.2014.00005

    CrossRef  Google Scholar 

  28. MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings Berkeley Symposium on Mathematical Statistics and Probability (1967)

    Google Scholar 

  29. Martinetz, T., Berkovich, S., Schulten, K.: Neural-gas network for vector quantization and its application to time-series prediction. IEEE Trans. Neural Netw. 4(4), 558–569 (1993). https://doi.org/10.1109/72.238311

    CrossRef  Google Scholar 

  30. Molina, A., Vergari, A., Di Mauro, N., Natarajan, S., Esposito, F., Kersting, K.: Mixed sum-product networks: a deep architecture for hybrid domains. In: Proceedings AAAI (2018)

    Google Scholar 

  31. Rao, S., Han, S., Principe, J.: Information theoretic vector quantization with fixed point updates. In: Proceedings IJCNN (2007)

    Google Scholar 

  32. Rojas, R.: Neural Networks – A Systematic Introduction. Springer, Heidelberg (1996)

    MATH  Google Scholar 

  33. Sifa, R.: An overview of Frank-Wolfe optimization for stochasticity constrained interpretable matrix and tensor factorization. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11140, pp. 369–379. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01421-6_36

    CrossRef  Google Scholar 

  34. Sifa, R., Bauckhage, C.: Online \(k\)-Maxoids clustering. In: Proceedings DSAA (2017)

    Google Scholar 

  35. Soper, A.: A higher order hopfield network for vector quantisation. Neural Comput. Appl. 7, 99–106 (1998). https://doi.org/10.1007/BF01414161

    CrossRef  MATH  Google Scholar 

  36. Xu, J.W., Paiva, A., Park, I., Principe, J.: A reproducing kernel Hilbert space framework for information-theoretic learning. IEEE Trans. Signal Process. 56(12), 5891–5902 (2008). https://doi.org/10.1109/TSP.2008.2005085

    MathSciNet  CrossRef  MATH  Google Scholar 

Download references

Acknowledgments

This work is a joint effort of the Fraunhofer Research Center for Machine Learning (FZML) within the Cluster of Excellence Cognitive Internet Technologies (CCIT) and the Competence Center for Machine Learning Rhine-Ruhr (ML2R). ML2R is funded by the Federal Ministry of Education and Research (BMBF) of Germany (grant no. 01IS18038A). The authors gratefully acknowledge this support.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to C. Bauckhage .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Bauckhage, C., Ramamurthy, R., Sifa, R. (2020). Hopfield Networks for Vector Quantization. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-61616-8_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-61615-1

  • Online ISBN: 978-3-030-61616-8

  • eBook Packages: Computer ScienceComputer Science (R0)