Learning Sparse Perceptrons

  title={Learning Sparse Perceptrons},
  author={Jeffrey C. Jackson and Mark Craven},
We introduce a new algorithm designed to learn sparse perceptrons over input representations which include high-order features. Our algorithm, which is based on a hypothesis-boosting method, is able to PAC-learn a relatively natural class of target concepts. Moreover, the algorithm appears to work well in practice: on a set of three problem domains, the algorithm produces classifiers that utilize small numbers of features yet exhibit good generalization performance. Perhaps most importantly… CONTINUE READING

From This Paper

Topics from this paper.
29 Citations
13 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 13 references

Learning internal representations by error propagation

  • D. Rumelhart, G. Hinton, R. Williams
  • 1986
Highly Influential
4 Excerpts

General bound on

  • Aslam, Decatur, J. A. 1993 Aslam, S. E. Decatur
  • 1993

General bound onstatistical query learning and PAC learning with noise via hypothesis boosting

  • J. Bruck
  • InProceedings of the 34 th Annual Symposium on…
  • 1993

Majoritygates vs . general weighted threshold gates

  • D. Haussler
  • Proceedings of the Seventh IEEE Conference on…
  • 1992

Optimal brain

  • Le Cun et al, Y. 1989 Le Cun, J. S. Denker, S. A. Solla
  • 1989

Similar Papers

Loading similar papers…