Refine
Year of publication
- 1999 (236) (remove)
Institute
- Fachbereich Wirtschaftswissenschaften (50)
- Fachbereich Medizintechnik und Technomathematik (40)
- Fachbereich Elektrotechnik und Informationstechnik (31)
- Fachbereich Energietechnik (28)
- Fachbereich Maschinenbau und Mechatronik (24)
- Fachbereich Luft- und Raumfahrttechnik (18)
- Fachbereich Chemie und Biotechnologie (16)
- Fachbereich Bauingenieurwesen (13)
- Solar-Institut Jülich (8)
- Fachbereich Gestaltung (6)
Document Type
- Article (153)
- Book (47)
- Conference Proceeding (17)
- Patent (7)
- Part of a Book (6)
- Report (3)
- Doctoral Thesis (1)
- Habilitation (1)
- Review (1)
Keywords
- Einspielen <Werkstoff> (2)
- Finite-Elemente-Methode (2)
- Traglast (2)
- shakedown analysis (2)
- 20 fossil-fueled power plants (1)
- Deponierverhalten (1)
- LISA (1)
- Lysimeter (1)
- MBRA (1)
- Müllsortierung (1)
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.
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.