The minimum feature set problem
β
Kevin S. Van Horn; Tony R. Martinez
π
Article
π
1994
π
Elsevier Science
π
English
β 334 KB
One approach to improving the generalization power of a neural net is to try to minimize the number of nonzero weights used. We examine two issues relevant to this approach, .for single-layer nets. First we bound the VC dimension of the set of linear-threshold fimctions that have nonzero weights fig