The minimum feature set problem

  title={The minimum feature set problem},
  author={Kevin S. Van Horn and Tony R. Martinez},
  journal={Neural Networks},
One approach to improving the generalization power of a neural net is to try to minimize the number of non-zero weights used. We examine two issues relevant to this approach, for single-layer nets. First we bound the VC dimension of the set of linearthreshold functions that have non-zero weights for at most s of n inputs. Second, we show that the problem of minimizing the number of non-zero input weights used (without misclassifying training examples) is both NP-hard and di cult to approximate. 
Highly Cited
This paper has 24 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 12 extracted citations

On the approximability of some NP-hard minimization problems for linear systems

Electronic Colloquium on Computational Complexity • 1996
View 7 Excerpts
Highly Influenced

Performance Evaluation of Automatic Feature Discovery Focused within Error Clusters

2010 20th International Conference on Pattern Recognition • 2010
View 1 Excerpt

Tight lower bounds for certain parameterized NP-hard problems

Proceedings. 19th IEEE Annual Conference on Computational Complexity, 2004. • 2004
View 1 Excerpt


Publications referenced by this paper.

Similar Papers

Loading similar papers…