Pixel based 3D object recognition with bidirectional associative memories
- 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.
| Verfasserangaben: | Ingo ElsenORCiD, Karl-Friedrich Kraiss, Dirk Krumbiegel |
|---|---|
| DOI: | https://doi.org/10.1109/ICNN.1997.614147 |
| ISBN: | 0-7803-4122-8 |
| Titel des übergeordneten Werkes (Englisch): | International Conference on Neural Networks 1997 |
| Verlag: | IEEE |
| Verlagsort: | New York |
| Dokumentart: | Konferenzveröffentlichung |
| Sprache: | Englisch |
| Erscheinungsjahr: | 1997 |
| Datum der Publikation (Server): | 13.04.2023 |
| Umfang: | 6 Seiten |
| Erste Seite: | 1679 |
| Letzte Seite: | 1684 |
| Bemerkung: | June 9 - 12, 1997, Westin Galleria Hotel Houston, Texas, USA. |
| Link: | https://ieeexplore.ieee.org/document/614147 |
| Zugriffsart: | campus |
| Fachbereiche und Einrichtungen: | FH Aachen / Fachbereich Elektrotechnik und Informationstechnik |
| FH Aachen / ECSM European Center for Sustainable Mobility | |
| collections: | Verlag / IEEE |
