Ensembles of Multi-Instance Neural Networks

@inproceedings{Zhang2004EnsemblesOM,
  title={Ensembles of Multi-Instance Neural Networks},
  author={Min-Ling Zhang and Zhi-Hua Zhou},
  booktitle={Intelligent Information Processing},
  year={2004}
}
Recently, multi-instance classification algorithm BP-MIP and multi-instance regression algorithm BP-MIR both based on neural networks have been proposed. In this paper, neural network ensemble techniques are introduced to solve multi-instance learning problems, where BP-MIP ensemble and BP-MIR ensemble are constructed respectively. Experiments on benchmark and artificial data sets show that ensembles of multi-instance neural networks are superior to single multi-instance neural networks in… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.
9 Citations
11 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 11 references

A neural network based multi-instance regression algorithm

  • Zhang, M.-L, Zhou, Z.-H
  • Journal of Software,
  • 2003
3 Excerpts

Neural networks for multi-instance learning

  • Zhou, Z.-H, Zhang, M.-L
  • Technical Report,
  • 2002
1 Excerpt

An Introduction to the Bootstrap

  • B. Efron, R. Tibshirani
  • 1993
1 Excerpt

Learning internal representations by error propagation

  • D. E. Rumelhart, G. E. Hinton, R. J. Williams
  • Nature
  • 1986

Similar Papers

Loading similar papers…