Visual Learning by Evolutionary Feature Synthesis

@inproceedings{Krawiec2003VisualLB,
  title={Visual Learning by Evolutionary Feature Synthesis},
  author={Krzysztof Krawiec and Bir Bhanu},
  booktitle={ICML},
  year={2003}
}
In this paper, we present a novel method for learning complex concepts/hypotheses directly from raw training data. The task addressed here concerns data-driven synthesis of recognition procedures for real-world object recognition task. The method uses linear genetic programming to encode potential solutions expressed in terms of elementary operations, and handles the complexity of the learning task by applying cooperative coevolution to decompose the problem automatically. The training consists… CONTINUE READING
Highly Cited
This paper has 21 citations. REVIEW CITATIONS
15 Citations
19 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 15 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 19 references

GEST: A learning computer vision system that recognizes hand gestures

  • J. Segen
  • Machine learning. A Multistrategy Approach
  • 1994
Highly Influential
3 Excerpts

ECJ Evolutionary Computation System

  • S. 266-273. Luke
  • 2002
2 Excerpts

An empirical analysis of collaboration methods in cooperative coevolutionary algorithms

  • R. P. Wiegand, W. C. Liles, K. A. De Jong
  • Proceedings of Genetic and Evolutionary…
  • 2001

Similar Papers

Loading similar papers…