Structural and Behavioral Evolution of Recurrent Networks

  title={Structural and Behavioral Evolution of Recurrent Networks},
  author={Gregory M. Saunders and Peter J. Angeline and Jordan B. Pollack},
This paper introduces GNARL, an evolutionary program which induces recurrent neural networks that are structurally unconstrained. In contrast to constructive and destructive algorithms, GNARL employs a population of networks and uses a fitness function’s unsupervised feedback to guide search through network space. Annealing is used in generating both gaussian weight changes and structural modifications. Applying GNARL to a complex search and collection task demonstrates that the system is… CONTINUE READING
9 Citations
20 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 20 references

Combinations of genetic algorithms and neural networks : A survey of the state of the art

  • J. D. Schaffer, D. Whitley, L. J. Eshelman
  • 1992

Genetic cascade learning for neural networks

  • N. Karunanithi, R. Das, D. Whitley
  • Proceedings of COGANN-92 International Workshop…
  • 1992
1 Excerpt

Genetic evolution and co-evolution of computer programs

  • J. Koza
  • Christopher G. Langton, Charles Taylor, J. D. F…
  • 1992
1 Excerpt

Evolution as a theme in artificial life: The genesys/tracker system

  • The University of Michigan Press, Ann Arbor, +7 authors A. Wang
  • Langton, C. G., Taylor, C., Farmer, J. D., and…
  • 1991

Similar Papers

Loading similar papers…