Refine
Year of publication
Document Type
- Article (625)
- Conference Proceeding (296)
- Book (113)
- Part of a Book (61)
- Patent (15)
- Report (9)
- Other (8)
- Contribution to a Periodical (6)
- Course Material (6)
- Doctoral Thesis (6)
- Bachelor Thesis (1)
- Video (1)
- Poster (1)
- Review (1)
- Talk (1)
Language
- English (693)
- German (456)
- Multiple languages (1)
Keywords
- Multimediamarkt (7)
- Enterprise Architecture (5)
- MINLP (5)
- Engineering optimization (4)
- Gamification (4)
- Serious Game (4)
- Auslenkung (3)
- Digitale Transformation (3)
- Digitalisierung (3)
- Education (3)
- Javasimulation (3)
- Literaturanalyse (3)
- Optimization (3)
- Powertrain (3)
- Referenzmodellierung (3)
- Robotic Process Automation (3)
- Technical Operations Research (3)
- Telecommunication (3)
- Amplitude (2)
- Autonomous mobile robots (2)
Institute
- Fachbereich Elektrotechnik und Informationstechnik (1150) (remove)
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.