Learning to recognize objects on the fly: A neurally based dynamic field approach

@article{Faubel2008LearningTR,
  title={Learning to recognize objects on the fly: A neurally based dynamic field approach},
  author={Christian Faubel and Gregor Sch{\"o}ner},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2008},
  volume={21 4},
  pages={
          562-76
        }
}
Autonomous robots interacting with human users need to build and continuously update scene representations. This entails the problem of rapidly learning to recognize new objects under user guidance. Based on analogies with human visual working memory, we propose a dynamical field architecture, in which localized peaks of activation represent objects over a small number of simple feature dimensions. Learning consists of laying down memory traces of such peaks. We implement the dynamical field… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 61 CITATIONS

Latency-based probabilistic information processing in a learning feedback hierarchy

  • 2014 International Joint Conference on Neural Networks (IJCNN)
  • 2014
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

The emergent executive: a dynamic field theory of the development of executive function.

  • Monographs of the Society for Research in Child Development
  • 2014
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Grounding Word Learning in Space

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Asymmetry in neural fields: a spatiotemporal encoding mechanism

  • Biological Cybernetics
  • 2012
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Dynamic neural field as framework for behaviour coordination in mobile robots

  • World Automation Congress 2012
  • 2012
VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2008
2019

CITATION STATISTICS

  • 8 Highly Influenced Citations

References

Publications referenced by this paper.