@article{ElsenKraissKrumbiegeletal.1999,
  author    = {Elsen, Ingo and Kraiss, Karl-Friedrich and Krumbiegel, Dirk and Walter, Peter and Wickel, Jochen},
  title     = {Visual information retrieval for 3D product identification: a midterm report},
  series = {KI - K{\"u}nstliche Intelligenz},
  volume    = {13},
  journal   = {KI - K{\"u}nstliche Intelligenz},
  number    = {1},
  publisher = {Springer},
  address   = {Berlin},
  issn      = {1610-1987},
  pages     = {64 -- 67},
  year      = {1999},
  language  = {en}
}
@article{ElsenKraiss1999,
  author    = {Elsen, Ingo and Kraiss, Karl-Friedrich},
  title     = {System concept and realization of a scalable neurocomputing architecture},
  series = {Systems Analysis Modelling Simulation},
  volume    = {35},
  journal   = {Systems Analysis Modelling Simulation},
  number    = {4},
  publisher = {Gordon and Breach Science Publishers},
  address   = {Amsterdam},
  issn      = {0232-9298},
  pages     = {399 -- 419},
  year      = {1999},
  abstract  = {This paper describes the realization of a novel neurocomputer which is based on the concepts of a coprocessor. In contrast to existing neurocomputers the main interest was the realization of a scalable, flexible system, which is capable of computing neural networks of arbitrary topology and scale, with full independence of special hardware from the software's point of view. On the other hand, computational power should be added, whenever needed and flexibly adapted to the requirements of the application. Hardware independence is achieved by a run time system which is capable of using all available computing power, including multiple host CPUs and an arbitrary number of neural coprocessors autonomously. The realization of arbitrary neural topologies is provided through the implementation of the elementary operations which can be found in most neural topologies.},
  language  = {en}
}
@inproceedings{ElsenKraissKrumbiegel1997,
  author    = {Elsen, Ingo and Kraiss, Karl-Friedrich and Krumbiegel, Dirk},
  title     = {Pixel based 3D object recognition with bidirectional associative memories},
  series = {International Conference on Neural Networks 1997},
  booktitle = {International Conference on Neural Networks 1997},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {0-7803-4122-8},
  pages     = {1679 -- 1684},
  year      = {1997},
  abstract  = {This paper addresses the pixel based recognition of 3D objects with bidirectional associative memories. Computational power and memory requirements for this approach are identified and compared to the performance of current computer architectures by benchmarking different processors. It is shown, that the performance of special purpose hardware, like neurocomputers, is between one and two orders of magnitude higher than the performance of mainstream hardware. On the other hand, the calculation of small neural networks is performed more efficiently on mainstream processors. Based on these results a novel concept is developed, which is tailored for the efficient calculation of bidirectional associative memories. The computational efficiency is further enhanced by the application of algorithms and storage techniques which are matched to characteristics of the application at hand.},
  language  = {en}
}
@inproceedings{WalterElsenMuelleretal.1999,
  author    = {Walter, Peter and Elsen, Ingo and M{\"u}ller, Holger and Kraiss, Karl-Friedrich},
  title     = {3D object recognition with a specialized mixtures of experts architecture},
  series = {IJCNN'99. International Joint Conference on Neural Networks. Proceedings},
  booktitle = {IJCNN'99. International Joint Conference on Neural Networks. Proceedings},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {0-7803-5529-6},
  issn      = {1098-7576},
  doi       = {10.1109/IJCNN.1999.836243},
  pages     = {3563 -- 3568},
  year      = {1999},
  abstract  = {Aim of the AXON2 project (Adaptive Expert System for Object Recogniton using Neuml Networks) is the development of an object recognition system (ORS) capable of recognizing isolated 3d objects from arbitrary views. Commonly, classification is based on a single feature extracted from the original image. Here we present an architecture adapted from the Mixtures of Eaqerts algorithm which uses multiple neuml networks to integmte different features. During tmining each neural network specializes in a subset of objects or object views appropriate to the properties of the corresponding feature space. In recognition mode the system dynamically chooses the most relevant features and combines them with maximum eficiency. The remaining less relevant features arz not computed and do therefore not decelerate the-recognition process. Thus, the algorithm is well suited for ml-time applications.},
  language  = {en}
}