@inproceedings {PUBA244,
	title = {Evolutionary generation of neural network update signals for the topology optimization of structures},
	author = {Nikola Aulig AND Markus Olhofer},
	year = {2013},
	month = {July},
	abstract = {In the adaptation of natural load bearing structures like bones and trees, regions subject to high physical loads accumulate structural material based on local stimuli, while it is reduced in others. This strategy can lead to efficient structures and has been modeled in the field of topology optimization. Instead of modeling the observed strategy we target the evolutionary process, which gave rise to theses strategies. We propose to use an evolutionary process in order to find a suitable mapping from local sensory information to an update signal, based on which a structure is adapted. The target is to evolve a generalizable update signal for quality functions that can not be optimized by existing topology optimization methods. As a first study, the update signal is represented by a feed-forward neural network
model and its weights are tuned by an evolutionary strategy in order to optimize a minimum compliance structure. The resulting update signal is subsequently compared to the true compliance sensitivities and indicate that evolving a neural network update signal by optimization is a demanding task, yet possible at least for the provided example problem.},
	publisher = {ACM},
	booktitle = {Genetic and Evolutionary Computation Conf. (GECCO Companion)},
	editor = {Blum, Christian and Alba, Enrique},
	pages = {213-214}
}