Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2008 Jun;127(2):187-94.
doi: 10.1007/s12064-008-0029-9. Epub 2008 Apr 16.

Neuroevolution and complexifying genetic architectures for memory and control tasks

Benjamin Inden  1
Affiliations

Neuroevolution and complexifying genetic architectures for memory and control tasks

Benjamin Inden. Theory Biosci. 2008 Jun.

Abstract

The way genes are interpreted biases an artificial evolutionary system towards some phenotypes. When evolving artificial neural networks, methods using direct encoding have genes representing neurons and synapses, while methods employing artificial ontogeny interpret genomes as recipes for the construction of phenotypes. Here, a neuroevolution system (neuroevolution with ontogeny or NEON) is presented that can emulate a well-known neuroevolution method using direct encoding (neuroevolution of augmenting topologies or NEAT), and therefore, can solve the same kinds of tasks. Performance on challenging control and memory benchmark tasks is reported. However, the encoding used by NEON is indirect, and it is shown how characteristics of artificial ontogeny can be introduced incrementally in different phases of evolutionary search.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Ontogeny with the neon method. In the middle are the genes, while on the right, the sequence of phenotypes is depicted
See this image and copyright information in PMC

References

    1. Bentley P, Kumar S (1999) Three ways to grow designs: a comparison of three embryogenies for an evolutionary design problem. In: Proceedings of the genetic and evolutionary computation conference
    1. Bongart J (2003) Incremental approaches to the combined evolution of a robot’s body and brain. Ph.D. thesis, Universität Zürich
    1. Eggenberger P (1996) Cell interactions as a control tool of developmental processes for evolutionary robotics. In: “From Animals to Animats 4”, 4th international conference on simulation of adaptive behavior
    1. Federici D. A regenerating spiking neural network. Neural Netw. 2005;18:746–754. doi: 10.1016/j.neunet.2005.06.006. - DOI - PubMed
    1. Green C (2006) SharpNEAT. http://www.sharpneat.sourceforge.net

Substances