Learning vector quantization for heterogeneous structured data

@inproceedings{Zhlke2010LearningVQ,
  title={Learning vector quantization for heterogeneous structured data},
  author={Dietlind Z{\"u}hlke and Frank-Michael Schleif and Tina Geweniger and Sven Haase and Thomas Villmann},
  booktitle={ESANN},
  year={2010}
}
In this paper we introduce an approach to integrate heterogeneous structured data into a learning vector quantization. The total distance between two heterogeneous structured samples is defined as a weighted sum of the distances in the single structural components. The weights are adapted in every iteration of learning using gradient descend on the cost function inspired by Generalized Learning Vector Quantization. The new method was tested on a real world data set for pollen recognition using… CONTINUE READING

Tables, Results, and Topics from this paper.

Key Quantitative Results

  • We than divided the data set into (1) pollen recognized with a reliability of at least 80% and (2) pollen recognized with less then 80% reliability.

References

Publications referenced by this paper.
SHOWING 1-3 OF 3 REFERENCES

PollenMonitor - a system for automatic determination of pollen concentration in ambient air

D. Zühlke, M. Häusler, U. Heimann
  • The 4th European Symposium on Aerobiology
  • 2008
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Generalized Learning Vector Quantization

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…