Tight bounds for the VC-dimension of piecewise polynomial networks

Akito Sakurai

研究成果: Conference contribution

7 被引用数 (Scopus)

抄録

0(ws(s log d+log(dqh/s))) and 0(ws((h/s) log q)+log[dqh/s)) are upper bounds for the VC-dimension of a set of neural networks of units with piecewise polynomial activation functions, where s is the depth of the network, h is the number of hidden units, w is the number of adjustable parameters, q is the maximum of the number of polynomial segments of the activation function, and d is the maximum degree of the polynomials; also ω{ωslog(dqh/s)) is a lower bound for the VC-dimension of such a network set, which are tight for the cases s = Θ(h) and s is constant. For the special case q = 1, the VC-dimension is Θ(ws\ogd).

本文言語English
ホスト出版物のタイトルAdvances in Neural Information Processing Systems 11 - Proceedings of the 1998 Conference, NIPS 1998
出版社Neural information processing systems foundation
ページ323-329
ページ数7
ISBN(印刷版)0262112450, 9780262112451
出版ステータスPublished - 1999 1 1
イベント12th Annual Conference on Neural Information Processing Systems, NIPS 1998 - Denver, CO, United States
継続期間: 1998 11 301998 12 5

出版物シリーズ

名前Advances in Neural Information Processing Systems
ISSN(印刷版)1049-5258

Other

Other12th Annual Conference on Neural Information Processing Systems, NIPS 1998
国/地域United States
CityDenver, CO
Period98/11/3098/12/5

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 情報システム
  • 信号処理

フィンガープリント

「Tight bounds for the VC-dimension of piecewise polynomial networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル