An Investigation of Artificial Neural Network Architectures in Artificial Life Implementations

Erdur, Serkan, and Tunga Güngör. “An Investigation of Artificial Neural Network Architectures in Artificial Life Implementations.” In International 13th Turkish Symposium on Artificial Intelligence and Neural Networks , pp. 191-199. 2004.
URL1 URL2

. In this paper, an artificially created world is defined and simulation results are presented. The proposed world is a complex system consisting of three types of agent: carnivorous, herbivorous, and plants. Agents live on a two-dimensional hypothetical world and have artificial neural network brains, which can learn over a life span and evolve over generations by genetic algorithms. Three senses, vision, smell, and hearing are implemented. A new version of Hebbian rule for short-term learning is defined. Each parameter was tested with numerous simulations and important guidelines were obtained that can direct the design of such artificial worlds.

Cited by 1
Related articles