Almost linear VC dimension bounds for piecewise polynomial networks

被引：0
|
作者：
Bartlett, PL [1 ]
Maiorov, V [1 ]
Meir, R [1 ]
机构：
[1] Australian Natl Univ, Dept Syst Engn, Canberra, ACT 0200, Australia
来源：
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 11 | 1999年 / 11卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We compute upper and lower bounds on the VC dimension of feedforward networks of units with piecewise polynomial activation functions. We show that if the number of layers is fixed, then the VC dimension grows as W log W, where W is the number of parameters in the network. This result stands in opposition to the case where the number of layers is unbounded, in which case the VC dimension grows as W-2.
引用
收藏
页码：190 / 196
页数：7
相关论文
共 50 条
  • [1] Almost linear VC-dimension bounds for piecewise polynomial networks
    Bartlett, PL
    Maiorov, V
    [J]. NEURAL COMPUTATION, 1998, 10 (08) : 2159 - 2173
  • [2] Tight bounds for the VC-dimension of piecewise polynomial networks
    Sakurai, A
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 11, 1999, 11 : 323 - 329
  • [3] Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks
    Bartlett, Peter L.
    Harvey, Nick
    Liaw, Christopher
    Mehrabian, Abbas
    [J]. Journal of Machine Learning Research, 2019, 20
  • [4] Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks
    Bartlett, Peter L.
    Harvey, Nick
    Liaw, Christopher
    Mehrabian, Abbas
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2019, 20 : 1 - 17
  • [5] Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
    Karpinski, M
    Macintyre, A
    [J]. JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1997, 54 (01) : 169 - 176
  • [6] VC dimension bounds for product unit networks
    Schmitt, M
    [J]. IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL IV, 2000, : 165 - 170
  • [7] On using the Poincare polynomial for calculating the VC dimension of neural networks
    Schmitt, M
    [J]. NEURAL NETWORKS, 2001, 14 (10) : 1465 - 1465
  • [8] BOUNDS IN PIECEWISE LINEAR TOPOLOGY
    TREYBIG, LB
    [J]. TRANSACTIONS OF THE AMERICAN MATHEMATICAL SOCIETY, 1975, 201 (JAN) : 383 - 405
  • [9] On specific stability bounds for linear multiresolution schemes based on piecewise polynomial Lagrange interpolation
    Amat, Sergio
    Donat, Rosa
    Carlos Trillo, J.
    [J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2009, 358 (01) : 18 - 27
  • [10] VC dimension bounds for analytic algebraic computations
    Montana, Jose Luis
    Pardo, Luis Miguel
    Callau, Mar
    [J]. COMPUTING AND COMBINATORICS, PROCEEDINGS, 2008, 5092 : 62 - 71
12345