@misc{SalberPischingerEschetal.1998,
  author    = {Salber, Wolfgang and Pischinger, Martin and Esch, Thomas and Hagen, J{\"u}rgen},
  title     = {Kaltstartverfahren f{\"u}r eine drosselfreie Mehrzylinder-Kolbenbrennkraftmaschine},
  year      = {1998},
  abstract  = {Die Erfindung betrifft ein Kaltstartverfahren f{\"u}r eine Mehrzylinder-Kolbenbrennkraftmaschine mit Anlasser und einer Motorsteuerung zur Ansteuerung von Kraftstoffeinspritzeinrichtungen, Z{\"u}ndung und voll variabel elektromagnetisch bet{\"a}tigbaren Gaswechselventilen an den einzelnen Zylindern, bei dem die Kurbelwelle {\"u}ber den Anlasser gedreht wird und zum Start f{\"u}r wenigstens einen Zylinder die dazugeh{\"o}rigen Gaswechselventile, die Kraftstoffeinspritzeinrichtung und die Z{\"u}ndung in einem vorgegebenen Taktzyklus angesteuert werden und zwar in den ersten Arbeitszyklen mit "Sp{\"a}tem Einlaß {\"O}ffnen".},
  language  = {de}
}
@inproceedings{Elsen1998,
  author    = {Elsen, Ingo},
  title     = {A pixel based approach to view based object recognition with self-organizing neural networks},
  series = {IECON'98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society},
  booktitle = {IECON'98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {0-7803-4503-7},
  doi       = {10.1109/IECON.1998.724032},
  pages     = {2040 -- 2044},
  year      = {1998},
  abstract  = {This paper addresses the pixel based classification of three dimensional objects from arbitrary views. To perform this task a coding strategy, inspired by the biological model of human vision, for pixel data is described. The coding strategy ensures that the input data is invariant against shift, scale and rotation of the object in the input domain. The image data is used as input to a class of self organizing neural networks, the Kohonen-maps or self-organizing feature maps (SOFM). To verify this approach two test sets have been generated: the first set, consisting of artificially generated images, is used to examine the classification properties of the SOFMs; the second test set examines the clustering capabilities of the SOFM when real world image data is applied to the network after it has been preprocessed to be invariant against shift, scale and rotation. It is shown that the clustering capability of the SOFM is strongly dependant on the invariance coding of the images.},
  language  = {en}
}