Skip to main content
SpringerLink
Log in

EvoDynamic: A Framework for the Evolution of Generally Represented Dynamical Systems and Its Application to Criticality

  • Conference paper
  • First Online:
Applications of Evolutionary Computation (EvoApplications 2020)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12104))

Abstract

Dynamical systems possess a computational capacity that may be exploited in a reservoir computing paradigm. This paper presents a general representation of dynamical systems which is based on matrix multiplication. That is similar to how an artificial neural network (ANN) is represented in a deep learning library and its computation can be faster because of the optimized matrix operations that such type of libraries have. Initially, we implement the simplest dynamical system, a cellular automaton. The mathematical fundamentals behind an ANN are maintained, but the weights of the connections and the activation function are adjusted to work as an update rule in the context of cellular automata. The advantages of such implementation are its usage on specialized and optimized deep learning libraries, the capabilities to generalize it to other types of networks and the possibility to evolve cellular automata and other dynamical systems in terms of connectivity, update and learning rules. Our implementation of cellular automata constitutes an initial step towards a more general framework for dynamical systems. Our objective is to evolve such systems to optimize their usage in reservoir computing and to model physical computing substrates. Furthermore, we present promising preliminary results toward the evolution of complex behavior and criticality using genetic algorithm in stochastic elementary cellular automata.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    EvoDynamic open-source repository is available at https://github.com/SocratesNFR/EvoDynamic.

  2. 2.

    Cluster size stands for the number of repetitions of a state that happened consecutively without any interruption of another state.

  3. 3.

    The actual number of histogram bins is normalized or divided by the possible total number of bins.

References

  1. SOCRATES – Self-Organizing Computational substRATES. https://www.ntnu.edu/socrates

  2. Conway’s game of life implemented using tensorflow 2d convolution function (2016). https://github.com/conceptacid/conv2d_life

  3. Aaser, P., et al.: Towards making a cyborg: a closed-loop reservoir-neuro system. In: The 2018 Conference on Artificial Life: A Hybrid of the European Conference on Artificial Life (ECAL) and the International Conference on the Synthesis and Simulation of Living Systems (ALIFE), no. 29, pp. 430–437 (2017). https://doi.org/10.1162/isal_a_072

  4. Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp. 265–283. USENIX Association, Savannah, GA (2016)

    Google Scholar 

  5. Alstott, J., Bullmore, E., Plenz, D.: Powerlaw: a python package for analysis of heavy-tailed distributions. PLOS ONE 9(1), 1–11 (2014). https://doi.org/10.1371/journal.pone.0085777

    Article  Google Scholar 

  6. Baetens, J.M., Van der Meeren, W., De Baets, B.: On the dynamics of stochastic elementary cellular automata. J. Cell. Automata 12, 63–80 (2016)

    MathSciNet  MATH  Google Scholar 

  7. Bak, P., Tang, C., Wiesenfeld, K.: Self-organized criticality: an explanation of the 1/f noise. Phys. Rev. Lett. 59, 381–384 (1987). https://doi.org/10.1103/PhysRevLett.59.381

    Article  Google Scholar 

  8. Broersma, H., Miller, J.F., Nichele, S.: Computational Matter: Evolving Computational Functions in Nanoscale Materials. In: Adamatzky, A. (ed.) Advances in Unconventional Computing. ECC, vol. 23, pp. 397–428. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-33921-4_16

    Chapter  Google Scholar 

  9. Clauset, A., Shalizi, C.R., Newman, M.E.: Power-law distributions in empirical data. SIAM Rev. 51(4), 661–703 (2009)

    Article  MathSciNet  Google Scholar 

  10. Gershenson, C.: Introduction to random boolean networks (2004). arXiv preprint nlin/0408006

    Google Scholar 

  11. Goldberg, D.E., Deb, K.: A comparative analysis of selection schemes used in genetic algorithms. In: Foundations of Genetic Algorithms, vol. 1, pp. 69–93. Elsevier (1991)

    Google Scholar 

  12. Goldstein, M.L., Morris, S.A., Yen, G.G.: Problems with fitting to the power-law distribution. Eur. Phys. J. B-Condens. Matter Complex Syst. 41(2), 255–258 (2004)

    Article  Google Scholar 

  13. Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004). https://doi.org/10.1126/science.1091277

    Article  Google Scholar 

  14. Jensen, J.H., Folven, E., Tufte, G.: Computation in artificial spin ice. In: The 2018 Conference on Artificial Life: A Hybrid of the European Conference on Artificial Life (ECAL) and the International Conference on the Synthesis and Simulation of Living Systems (ALIFE), no. 30, pp. 15–22 (2018). https://doi.org/10.1162/isal_a_00011

  15. Kaneko, K.: Overview of coupled map lattices. Chaos: Interdisc. J. Nonlinear Sci. 2(3), 279–282 (1992)

    Article  MathSciNet  Google Scholar 

  16. Konkoli, Z., Nichele, S., Dale, M., Stepney, S.: Reservoir Computing with Computational Matter. Comput. Matter. NCS, pp. 269–293. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-65826-1_14

    Chapter  MATH  Google Scholar 

  17. Langton, C.G.: Computation at the edge of chaos: phase transitions and emergent computation. Phys. D: Nonlinear Phenom. 42(1), 12–37 (1990). https://doi.org/10.1016/0167-2789(90)90064-V

    Article  MathSciNet  Google Scholar 

  18. Maass, W., Markram, H.: On the computational power of circuits of spiking neurons. J. Comput. Syst. Sci. 69(4), 593–616 (2004). https://doi.org/10.1016/j.jcss.2004.04.001

    Article  MathSciNet  MATH  Google Scholar 

  19. Nichele, S., Tufte, G.: Trajectories and attractors as specification for the evolution of behaviour in cellular automata. In: IEEE Congress on Evolutionary Computation, pp. 1–8, July 2010. https://doi.org/10.1109/CEC.2010.5586115

  20. Nichele, S., Farstad, S.S., Tufte, G.: Universality of evolved cellular automata in-materio. Int. J. Unconv. Comput. 13(1) (2017)

    Google Scholar 

  21. Nichele, S., Gundersen, M.S.: Reservoir computing using nonuniform binary cellular automata. Complex Syst. 26(3), 225–245 (2017). https://doi.org/10.25088/complexsystems.26.3.225

    Article  MathSciNet  MATH  Google Scholar 

  22. Nichele, S., Molund, A.: Deep learning with cellular automaton-based reservoir computing. Complex Syst. 26(4), 319–339 (2017). https://doi.org/10.25088/complexsystems.26.4.319

    Article  MathSciNet  Google Scholar 

  23. Nichele, S., Tufte, G.: Genome parameters as information to forecast emergent developmental behaviors. In: Durand-Lose, J., Jonoska, N. (eds.) UCNC 2012. LNCS, vol. 7445, pp. 186–197. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32894-7_18

    Chapter  Google Scholar 

  24. Rendell, P.: Turing Universality of the Game of Life, pp. 513–539. Springer, London (2002). https://doi.org/10.1007/978-1-4471-0129-1_18

    Book  Google Scholar 

  25. Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks 2007, pp. 471–482 (2007)

    Google Scholar 

  26. Subramoney, A., Scherr, F., Maass, W.: Reservoirs learn to learn (2019). arXiv preprint arXiv:1909.07486

  27. Tanaka, G., et al.: Recent advances in physical reservoir computing: a review. Neural Netw. 115, 100–123 (2019). https://doi.org/10.1016/j.neunet.2019.03.005

    Article  Google Scholar 

  28. TensorFlow: tf.sparse.sparse\_dense\_matmul | tensorflow core r1.14 | tensorflow. https://www.tensorflow.org/api_docs/python/tf/sparse/sparse_dense_matmul

  29. Toffoli, T., Margolus, N.: Cellular Automata Machines: A New Environment for Modeling. MIT press, Cambridge (1987)

    Book  Google Scholar 

  30. Wolfram, S.: A New Kind of Science, vol. 5. Wolfram Media, Champaign (2002)

    MATH  Google Scholar 

  31. Wright, S.: Correlation and causation. J. Agric. Res. 20, 557–580 (1921)

    Google Scholar 

Download references

Acknowledgments

We thank Kristine Heiney for thoughtful discussions about self-organized criticality.

Author information

Authors and Affiliations

  1. Department of Computer Science, Oslo Metropolitan University, Oslo, Norway

    Sidney Pontes-Filho, Pedro Lind, Anis Yazidi, Jianhua Zhang, Hugo Hammer, Gustavo B. M. Mello & Stefano Nichele

  2. Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway

    Sidney Pontes-Filho & Gunnar Tufte

  3. Department of Neuromedicine and Movement Science, Norwegian University of Science and Technology, Trondheim, Norway

    Ioanna Sandvig

  4. Holistic Systems, SimulaMet, Oslo, Norway

    Stefano Nichele

Authors
  1. Sidney Pontes-Filho
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pedro Lind
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Anis Yazidi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jianhua Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hugo Hammer
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Gustavo B. M. Mello
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ioanna Sandvig
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Gunnar Tufte
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Stefano Nichele
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sidney Pontes-Filho .

Editor information

Editors and Affiliations

  1. University of Granada, Granada, Spain

    Pedro A. Castillo

  2. Université Le Havre Normandie, Le Havre, France

    Juan Luis Jiménez Laredo

  3. Universidad de Extremadura, Mérida, Spain

    Francisco Fernández de Vega

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Pontes-Filho, S. et al. (2020). EvoDynamic: A Framework for the Evolution of Generally Represented Dynamical Systems and Its Application to Criticality. In: Castillo, P.A., Jiménez Laredo, J.L., Fernández de Vega, F. (eds) Applications of Evolutionary Computation. EvoApplications 2020. Lecture Notes in Computer Science(), vol 12104. Springer, Cham. https://doi.org/10.1007/978-3-030-43722-0_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-43722-0_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-43721-3

  • Online ISBN: 978-3-030-43722-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation