Advertisement

Evolving Memristive Neural Networks

  • Gerard David HowardEmail author
  • Larry Bull
  • Ben De Lacy Costello
  • Ella Gale
  • Andrew Adamatzky
Chapter

Abstract

Of the many network representations in which memristors can be modelled, neural networks are perhaps the most enticing as they open the possibility for neuromorphic computing—biologically-inspired brainlike information processing in hardware. Memristors are analogous to biological synapses; both feature nonvolatile resistance, a charge-dependent plastic response to activity, and can provide adaptive learning when coupled with a Hebbian mechanism. In this chapter, various types of memristors are deployed as synapses in spiking networks. Biological information processing implies autonomous learning control—a neuro-evolutionary approach provides this functionality and is used to search for beneficial network topologies. The main focus of this work extends the remit of the evolutionary algorithm to alter the conductance profiles of individual memristors, creating networks of heterogeneous variable synapses. These variable memristor networks are tested against networks of benchmark synapses in a robotic pathfinding scenario. Experimental findings conclude that the variable synapses bestow more behavioural degrees of freedom to the networks, allowing them to outperform the comparative synapse types.

Notes

Acknowledgements

This work was funded by EPSRC grant number EP/H014381/1.

References

  1. 1.
    Abbott, L., Regehr, W.: Synaptic computation. Nature 431, 796–803 (2004)CrossRefGoogle Scholar
  2. 2.
    Afifi, A., Ayatollahi, A., Raissi, F.: Stdp implementation using memristive nanodevice in cmos-nano neuromorphic networks. IEICE Electron. Express 6(3), 148–153 (2009)CrossRefGoogle Scholar
  3. 3.
    Akinaga, B.H., Shima, H.: Resistive random access memory (reram) based on metal oxides. Proc. IEEE 98(12), 2237–2251 (2010)CrossRefGoogle Scholar
  4. 4.
    Chua, L.: Memristor—the missing circuit element. IEEE Trans. Circuit Theory 18(5), 507–519 (1971).  https://doi.org/10.1109/TCT.1971.1083337CrossRefGoogle Scholar
  5. 5.
    Chua, L., Sbitnev, V., Kim, H.: Hodgkin huxley axon is made of memristors. Int. J. Bifurcat. Chaos 22(03), 1230,011 (2012)CrossRefGoogle Scholar
  6. 6.
    Dolan, C.P., Dyer, M.G.: Toward the evolution of symbols. In: Grefenstette, J.J. (ed.) Genetic Algorithms and their Applications (ICGA’87), pp. 123–131. Lawrence Erlbaum Associates, Hillsdale, New Jersey (1987)Google Scholar
  7. 7.
    Doolittle, W., Calley, W., Henderson, W.: Complementary oxide memristor technology facilitating both inhibitory and excitatory synapses for potential neuromorphic computing applications. In: Semiconductor Device Research Symposium, 2009. ISDRS ’09. International, pp. 1–2 (2009)Google Scholar
  8. 8.
    Durr, P., Mattiussi, C., Soltoggio, A., Floreano, D.: Evolvability of neuromodulated learning for robots. In: Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, pp. 41–46. IEEE Computer Society, Los Alamitos, CA (2008)Google Scholar
  9. 9.
    Erokhin, V.: On the learning of stochastic networks of organic memristive devices. IJUC 9(3–4), 303–310 (2013)Google Scholar
  10. 10.
    Erokhin, V., Fontana, M.P.: Electrochemically controlled polymeric device: a memristor (and more) found two years ago (2008). ArXiv e-prints 0807.0333
  11. 11.
    Erokhin, V., Howard, G.D., Adamatzky, A.: Organic memristor devices for logic elements with memory. Int. J. Bifurcat. Chaos 22(11), 1250283 (2012)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Floreano, D., Durr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intell. 1, 47–62 (2008)CrossRefGoogle Scholar
  13. 13.
    Gale, E.: The memory-conservation model of memristance. In: Heber, J., Schlom, D., Tokura, Y., Waser, R., Wutting, M. (eds.) Technical Digest of Frontiers in Electronic Materials, pp. 538–539. Nature Conferences & Wiley VCH (2012)Google Scholar
  14. 14.
    Gale, E., de Lacy Costello, B., Adamatzky, A.: The effect of electrode size on memristor properties: an experimental and theoretical study. In: International Conference in Electronics Design, Systems and Applications (ICEDSA 2012) (2012)Google Scholar
  15. 15.
    Gerstner, W., Kistler, W.: Spiking Neuron Models—Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge (2002)CrossRefGoogle Scholar
  16. 16.
    Hebb, D.O.: The Organisation of Behavior. Wiley, New York (1949)Google Scholar
  17. 17.
    Holland, J.H.: Adaptation in Natural and Artificial Systems. The University of Michigan Press, Ann Arbor (1975)Google Scholar
  18. 18.
    Hosoi, Y., Tamai, Y., Ohnishi, T., Ishihara, K., Shibuya, T., Inoue, Y., Yamazaki, S., Nakano, T., Ohnishi, S., Awaya, N., et al.: High speed unipolar switching resistance ram (rram) technology. In: 2006 International Electron Devices Meeting, vol. 1, pp. 1–4 (2006)Google Scholar
  19. 19.
    Howard, G., Gale, E., Bull, L., de Lacy, Costello B., Adamatzky, A.: Evolution of plastic learning in spiking networks via memristive connections. IEEE Trans. Evol. Comput. 16(5), 711–729 (2012a)CrossRefGoogle Scholar
  20. 20.
    Howard, G.D.: Constructivist and spiking neural learning classifier systems. Ph.D. thesis, University of the West of England (2010)Google Scholar
  21. 21.
    Howard, G.D., Bull, L., Adamatzky, A.: Cartesian genetic programming for memristive logic circuits. In: Moraglio, A., Silva, S., Krawiec, K., Machado, P., Cotta, C. (eds.) Proceedings of the 15th European Conference on Genetic Programming, EuroGP 2012. LNCS, vol. 7244, pp. 37–48. Springer, Malaga, Spain (2012b)Google Scholar
  22. 22.
    Howard, G.D., Bull, L., Costello, B.D.L., Adamatzky, A., Erokhin, V.: Creating unorganised machines from memristors. Int. J. Appl. Math. Inf. Sci. 7(4), 1275–1283 (2013)CrossRefGoogle Scholar
  23. 23.
    Howard, G.D., Bull, L., Costello, B.D.L., Gale, E., Adamatzky, A.: Evolving spiking networks with variable resistive memories. Evol. Comput. 22(1), 79–103, MIT Press, Cambridge, MA, USA (2014)Google Scholar
  24. 24.
    Hurst, J., Bull, L.: A neural learning classifier system with self-adaptive constructivism for mobile robot control. Artif. Life 12(3), 353–380 (2006)CrossRefGoogle Scholar
  25. 25.
    Jo, S.H., Chang, T., Ebong, I., Bhadviya, B.B., Mazumder, P., Lu, W.: Nanoscale memristor device as synapse in neuromorphic systems. Nano Lett. 10(4), 1297–1301 (2010)CrossRefGoogle Scholar
  26. 26.
    Kistler, W.M.: Spike-timing dependent synaptic plasticity: a phenomenological framework. Biol. Cybern. 87(5–6), 416–427 (2002)CrossRefGoogle Scholar
  27. 27.
    Linares-Barranco, B., Serrano-Gotarredona, T.: Memristance can explain spike-time-dependent-plasticity in neural synapses. In: Nature Precedings (2009)Google Scholar
  28. 28.
    Liu, S., Wu, N., Ignatiev, A.: Electric-pulse-induced reversible resistance change effect in magnetoresistive films. Appl. Phys. Lett. 76(19), 2749–2751 (2000)CrossRefGoogle Scholar
  29. 29.
    Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10, 1659–1671 (1996)CrossRefGoogle Scholar
  30. 30.
    Maass, W., Zador, A.M.: Dynamic stochastic synapses as computational units. Neural Comput. 11(4), 903–917 (1999)CrossRefGoogle Scholar
  31. 31.
    Mead, C.: Neuromorphic electronic systems. Proc. IEEE 78(10), 1629–1636 (1990)CrossRefGoogle Scholar
  32. 32.
    Michel, O.: Webots\(^{TM}\): professional mobile robot simulation. Int. J. Adv. Rob. Syst. 1(1), 39–42 (2004)Google Scholar
  33. 33.
    Mouttet, B.: Memristor pattern recognition circuit architecture for robotics. In: Proceedings of the 2nd International Multi-Conference on Engineering and Technological Innovation II, pp. 65–70 (2009)Google Scholar
  34. 34.
    Nolfi, S., Floriano, D.: Evolutionary Robotics. The MIT Press, Cambridge, MA (2000)Google Scholar
  35. 35.
    Pershin, Y.V., La Fontaine, S., Di Ventra, M.: Memristive model of amoeba learning. Phys. Rev. E 80(2), 021,926 (2009).  https://doi.org/10.1103/PhysRevE.80.021926CrossRefGoogle Scholar
  36. 36.
    Querlioz, D., Bichler, O., Gamrat, C.: Simulation of a memristor-based spiking neural network immune to device variations. In: Proceedings of the 2011 International Joint Conference on Neural Networks (IJCNN), pp. 1775–1781. IEEE, San Jose, CA, USA (2011)Google Scholar
  37. 37.
    Rechenberg, I.: Evolutionsstrategie: optimierung technischer systeme nach prinzipien der biologischen evolution. Frommann-Holzboog (1973)Google Scholar
  38. 38.
    Rocha, M., Cortez, P., Neves, J.: Evolutionary neural network learning. Progress in Artificial Intelligence. Lecture Notes in Computer Science, vol. 2902, pp. 24–28. Springer, Berlin (2003)CrossRefGoogle Scholar
  39. 39.
    Rumelhart, D., McClelland, J.: Parallel Distributed Processing, vols. 1 & 2. MIT Press, Cambridge, MA (1986)Google Scholar
  40. 40.
    Saggie-Wexler, K., Keinan, A., Ruppin, E.: Neural processing of counting in evolved spiking and McCulloch-Pitts agents. Artif. Life 12(1), 1–16 (2006)CrossRefGoogle Scholar
  41. 41.
    Snider, G.: Computing with hysteretic resistor crossbars. Appl. Phys. A 80, 1165–1172 (2005)CrossRefGoogle Scholar
  42. 42.
    Snider, G.: Spike-timing-dependent learning in memristive nanodevices. In: IEEE International Symposium on Nanoscale Architectures, 2008. NANOARCH 2008, pp. 85–92 (2008)  https://doi.org/10.1109/NANOARCH.2008.4585796
  43. 43.
    Soltoggio, A.: Neural plasticity and minimal topologies for reward-based learning. In: Proceedings of the 2008 8th International Conference on Hybrid Intelligent Systems, pp. 637–642. IEEE Computer Society, Washington, DC, USA (2008)Google Scholar
  44. 44.
    Strukov, D.B., Snider, G.S., Stewart, D.R., Williams, R.S.: The missing memristor found. Nature 453, 80–83 (2008)CrossRefGoogle Scholar
  45. 45.
    Strukov, D.B., Borghetti, J.L., Williams, R.S.: Coupled ionic and electronic transport model of thin-film semiconductor memristive behavior. Small 5(9), 1058–1063 (2009)CrossRefGoogle Scholar
  46. 46.
    Urzelai, J., Floreano, D.: Evolution of adaptive synapses: robots with fast adaptive behavior in new environments. Evol. Comput. 9, 495–524 (2001)CrossRefGoogle Scholar
  47. 47.
    Vujisic, M., Stankovic, K., Marianovic, N., Osmokrovic, P.: Simulated effects of proton and ion beam irradiation on titanium dioxide memristors. IEEE Trans. Nucl. Sci. 57(4), 1798–1804 (2010)CrossRefGoogle Scholar
  48. 48.
    Wang, X., Chen, Y.: Spintronic memristor devices and application. In: Proceedings of the Conference on Design, Automation and Test in Europe, European Design and Automation Association, pp. 667–672 (2010)Google Scholar
  49. 49.
    Waser, R., Aono, M.: Nanoionics-based resistive switching memories. Nat. Mater. 6(11), 833–840 (2007)CrossRefGoogle Scholar
  50. 50.
    Xia, G., Tang, Z., Li, Y., Wang, J.: A binary hopfield neural network with hysteresis for large crossbar packet-switches. Neurocomputing 67, 417–425 (2005)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Gerard David Howard
    • 1
    Email author
  • Larry Bull
    • 1
  • Ben De Lacy Costello
    • 1
  • Ella Gale
    • 1
  • Andrew Adamatzky
    • 1
  1. 1.University of the West of EnglandBristolUK

Personalised recommendations