GasNets and CTRNNs – A Comparison in Terms of Evolvability

  • Sven Magg
  • Andrew Philippides
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)


In the last few years a lot of work has been done to discover why GasNets outperform other network types in terms of evolvability. In this work GasNets are again compared to CTRNNs on a shape discrimination task. This task is used as to solve it, or gain an advantage, a controller does not need timers or pattern generators. We show that GasNets are outperformed by CTRNNs in terms of evolvability on this task and possible reasons for the disadvantages of GasNets are investigated. It is shown that, on a simple task where there is no necessity for a timer or pattern generator, there may be other issues which are better tackled by CTRNNs.


Good Individual Average Fitness Artificial Life Network Type Dynamical Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beer, R.D.: On the dynamics of small continuous-time recurrent neural networks. Adaptive Behavior 3(4), 471–511 (1995)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Beer, R.D.: Toward the evolution of dynamical neural networks for minimally cognitive behavior. In: Maes, P., Mataric, M., Meyer, J., Pollack, J., Wilson, S. (eds.) From animals to animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, pp. 421–429. MIT Press, Cambridge (1996)Google Scholar
  3. 3.
    Funahashi, K.: On the approximate realization of continuous mappings by neural networks. Neural Networks 2, 183–192 (1989)CrossRefGoogle Scholar
  4. 4.
    Husbands, P., Smith, T., Jakobi, N., O’Shea, M.: Better living through chemistry: Evolving GasNets for robot control. Connection Science 10(3-4), 185–210 (1998)CrossRefGoogle Scholar
  5. 5.
    McHale, G., Husbands, P.: GasNets and other Evolvable Neural Networks applied to Bipedal Locomotion. In: From Animals to Animats 8: Proceedings of the Eigth International Conference on Simulation of Adaptive Behavior (SAB 2004) (2004)Google Scholar
  6. 6.
    McHale, G., Husbands, P.: Quadrupedal Locomotion: GasNets, CTRNNs and Hybrid CTRNN/PNNs Compared. In: Pollack, J., Bedau, M., Husbands, P., Ikegami, T., Watson, R.A. (eds.) Artificial Life IX: Proceedings of the Ninth International Conference on the Simulation and Synthesis of Living Systems, pp. 106–113. MIT Press, Cambridge (2004)Google Scholar
  7. 7.
    Philippides, A., Husbands, P., Smith, T., O’Shea, M.: Flexible couplings: diffusing neuromodulators and adaptive robotics. Artificial Life 11(1&2), 139–160 (2005)CrossRefGoogle Scholar
  8. 8.
    Philippides, A.O., Husbands, P., Smith, T., O’Shea, M.: Fast and Loose: Biologically Inspired Couplings. In: Standish, R.K., Bedau, M.A., Abbass, H.A. (eds.) Artificial life VIII. Proceedings of the 8th international conference on artificial life, pp. 292–301. MIT Press, Cambridge (2002)Google Scholar
  9. 9.
    Philippides, A.: Personal communication Google Scholar
  10. 10.
    Slocum, A.C., Downey, D.C., Beer, R.D.: Further experiments in the evolution of minimally cognitive behavior: From perceiving affordances to selective attention. In: Meyer, J., Berthoz, A., Floreano, D., Roitblat, H., Wilson, S. (eds.) From Animals to Animats 6: Proceedings of the Sixth International Conference on Simulation of Adaptive Behavior, pp. 430–439. MIT Press, Cambridge (2000)Google Scholar
  11. 11.
    Smith, T., Husbands, P., Philippides, A., O’Shea, M.: Temporally adaptive networks: analysis of GasNet robot control networks. In: Standish, R.K., Bedau, M.A., Abbass, H.A. (eds.) Proceedings of the Eighth international Conference on Artificial Life, pp. 274–282. MIT Press, Cambridge (2003)Google Scholar
  12. 12.
    Smith, T.: The evolvability of artificial neural networks for robot control. PhD Thesis. School of Biological Sciences, University of Sussex (2002)Google Scholar
  13. 13.
    Smith, T.M.C., Philippides, A.: Nitric Oxide Signalling in Real and Artificial Neural Networks. British Telecom Technology Journal 18(4), 140–149 (2000)Google Scholar
  14. 14.
    Smith, T.M.C., Philippides, A., Husbands, P., O’Shea, M.: Neutrality and Ruggedness in Robot Landscapes. In: Congress on Evolutionary Computation: CEC 2002, pp. 1348–1353. IEEE Press, Los Alamitos (2002)Google Scholar
  15. 15.
    Yamauchi, B., Beer, R.D.: Sequential behavior and learning in evolved dynamical neural networks. Adaptive Behavior 2(3), 219–246 (1994)CrossRefGoogle Scholar
  16. 16.
    Magg, S.: CTRNNs and GasNets: A comparison in terms of evolvability. Master Thesis, Department of Informatics, University of Sussex (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sven Magg
    • 1
    • 2
  • Andrew Philippides
    • 2
  1. 1.Department of Informatics 
  2. 2.Centre for Computational Neuroscience and RoboticsUniversity of Sussex 

Personalised recommendations