Heidl, W.; Eitzinger, C.; Gyimesi, M.; Breitenecker, F. - In: Mathematics and Computers in Simulation (MATCOM) 82 (2011) 3, pp. 442-449
Numerous applications benefit from parts-based representations resulting in sets of feature vectors. To apply standard machine learning methods, these sets of varying cardinality need to be aggregated into a single fixed-length vector. We have evaluated three common Recurrent Neural Network...
