The Effect of Connection Cost on Modularity in Evolved Neural Networks
Jessica Lowell, Jordan B. Pollack · 2014
Modularity, often observed in biological systems, does not easily arise in computational evolution. We explore the effect of adding a small fitness cost for each connection between neurons on the modularity of neural networks produced by the NEAT neuroevolution algorithm. We find that this con-nection cost does not increase the modularity of the best net-work produced by each run of the algorithm, but that it does lead to increased consistency in the level of modularity pro-duced by the algorithm.