Abstract
One of the central questions of biology is how complex biological systems can continue functioning in the presence of perturbations, damage, and mutational insults. This paper investigates evolution of spiking neural networks, consisting of adaptive exponential neurons. The networks are encoded in linear genomes in a manner inspired by genetic networks. The networks control a simple animat, with two sensors and two actuators, searching for targets in a simple environment. The results show that the presence of noise on the membrane voltage during evolution allows for evolution of efficient control and robustness to perturbations to the value of the neural parameters of neurons.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Braitenberg, V.: Vehicles. Experiments in Synthetic Psychology. MIT Press, Cambridge (1986)
Brette, R., Gerstner, W.: Adaptive exponential integrate-and-fire model as an effective description of neuronal activity. J. Neurophysiol. 94(5), 3637–3642 (2005)
Joachimczak, M., Wróbel, B.: Evolving gene regulatory networks for real time control of foraging behaviours. In: Proceedings of the Alife XII Conference, pp. 348–358. MIT Press, Cambridge (2010)
Joachimczak, M., Wróbel, B.: Evolution of robustness to damage in artificial 3-dimensional development. Biosystems 109(3), 498–505 (2012)
Naud, R., Marcille, N., Clopath, C., Gerstner, W.: Firing patterns in the adaptive exponential integrate-and-fire model. Biol. Cybern. 99(4–5), 335–347 (2008)
Stromatias, E., Neil, D., Pfeiffer, M., Galluppi, F., Furber, S.B., Liu, S.C.: Robustness of spiking deep belief networks to noise and reduced bit precision of neuro-inspired hardware platforms. Front. Neurosci. 9 (2015). paper number 222
Wagner, A.: Robustness and Evolvability in Living Systems. Princeton University Press, Princeton (2013)
Wróbel, B., Abdelmotaleb, A., Joachimczak, M.: Evolving networks processing signals with a mixed paradigm, inspired by gene regulatory networks and spiking neurons. In: Di Caro, G.A., Theraulaz, G. (eds.) International Conference on Bio-Inspired Models of Network, Information, and Computing Systems, BIONETICS 2012. LNICST, vol. 134, pp. 135–149. Springer, Heidelberg (2014)
Wróbel, B., Joachimczak, M.: Using the genetic regulatory evolving artificial networks (GReaNs) platform for signal processing, animat control, and artificial multicellular development. In: Kowaliw, T., Bredeche, N., Doursat, R. (eds.) Growing Adaptive Machines. SCI, vol. 557, pp. 187–200. Springer, Heidelberg (2014)
Acknowledgments
This work was supported by Polish National Science Centre (project EvoSN, UMO-2013/08/M/ST6/00922). I am grateful to Volker Steuber for discussions, and to Ahmed Abdelmotaleb and Michal Joachimczak for their involvement in the development of GReaNs software platform.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Wróbel, B. (2016). Evolution of Spiking Neural Networks Robust to Noise and Damage for Control of Simple Animats. In: Handl, J., Hart, E., Lewis, P., López-Ibáñez, M., Ochoa, G., Paechter, B. (eds) Parallel Problem Solving from Nature – PPSN XIV. PPSN 2016. Lecture Notes in Computer Science(), vol 9921. Springer, Cham. https://doi.org/10.1007/978-3-319-45823-6_64
Download citation
DOI: https://doi.org/10.1007/978-3-319-45823-6_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45822-9
Online ISBN: 978-3-319-45823-6
eBook Packages: Computer ScienceComputer Science (R0)