@article{WiegandIgelHandmann2004, author = {Stefan Wiegand and Christian Igel and Uwe Handmann}, title = {Evolutionary multi-objective optimization of neural networks for face detection}, series = {International Journal of Computational Intelligence and Applications}, volume = {2004}, number = {4(3)}, doi = {10.1142/S1469026804001288}, pages = {237 -- 253}, year = {2004}, abstract = {For face recognition from video streams speed and accuracy are vital aspects. The first decision whether a preprocessed image region represents a human face or not is often made by a feed-forward neural network (NN), e.g. in the Viisage-FaceFINDER® video surveillance system. We describe the optimisation of such a NN by a hybrid algorithm combining evolutionary multi-objective optimisation (EMO) and gradient-based learning. The evolved solutions perform considerably faster than an expert-designed architecture without loss of accuracy. We compare an EMO and a single objective approach, both with online search strategy adaptation. It turns out that EMO is preferable to the single objective approach in several respects.}, language = {en} }