Ehresmann connections and feedforward neural networks

被引：0
|
作者：
Pearson, DW [1 ]
机构：
[1] EMA, LGI2P, Nonlinear & Uncertain Syst Grp, F-30035 Nimes 1, France
来源：
MATHEMATICAL AND COMPUTER MODELLING | 1999年 / 29卷 / 09期
关键词：
Ehresmann connections; feedforward neural networks; vertical vector fields;
D O I：
10.1016/S0895-7177(99)00078-3
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
In this paper, we describe how Ehresmann connections can be used to study certain properties of feedforward neural networks. Essentially, we calculate a Lie group approximation to the structure of the inverse image set above a certain point in the output space and this structure can then be locally transported to the inverse image above a, neighbouring point in the output space by means of an Ehresmann connection. This enables us to find a continuous approximation to the underlying topological structure of the data from discrete data pairs (input/output pairs). (C) 1999 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码：17 / 25
页数：9
相关论文
共 50 条
  • [41] FUNCTIONALLY EQUIVALENT FEEDFORWARD NEURAL NETWORKS
    KURKOVA, V
    KAINEN, PC
    NEURAL COMPUTATION, 1994, 6 (03) : 543 - 558
  • [42] A constructive algorithm for feedforward neural networks
    Institute of System Science, East China Normal University
    不详
    不详
    1600, 659-664 (2004):
  • [43] FEEDFORWARD NEURAL NETWORKS - A GEOMETRICAL PERSPECTIVE
    BUDINICH, M
    MILOTTI, E
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1991, 24 (04): : 881 - 888
  • [44] Quantum neural networks (QNNs): Inherently fuzzy feedforward neural networks
    Purushothaman, G
    Karayiannis, NB
    ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 1085 - 1090
  • [45] Training feedforward neural networks using neural networks and genetic algorithms
    Tellez, P
    Tang, Y
    INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATIONS AND CONTROL TECHNOLOGIES, VOL 1, PROCEEDINGS, 2004, : 308 - 311
  • [46] Survey on Robustness Verification of Feedforward Neural Networks and Recurrent Neural Networks
    Liu Y.
    Yang P.-F.
    Zhang L.-J.
    Wu Z.-L.
    Feng Y.
    Ruan Jian Xue Bao/Journal of Software, 2023, 34 (07): : 1 - 33
  • [47] Singular foliations with ehresmann connections and their holonomy groupoids
    Zhukova, Nina I.
    GEOMETRY AND TOPOLOGY OF MANIFOLDS: THE MATHEMATICAL LEGACY OF CHARLES EHRESMANN ON THE OCCASION OF THE HUNDREDTH ANNIVERSARY OF HIS BIRTHDAY, 2007, 76 : 471 - 490
  • [48] Protein Prediction with Neural Networks: FeedForward Networks Recurring Networks
    Cardenas Quintero, Beitmantt Geovanni
    REVISTA FACULTAD DE INGENIERIA, UNIVERSIDAD PEDAGOGICA Y TECNOLOGICA DE COLOMBIA, 2007, 16 (23): : 75 - 87
  • [49] Riemannian metrics for neural networks I: feedforward networks
    Ollivier, Yann
    INFORMATION AND INFERENCE-A JOURNAL OF THE IMA, 2015, 4 (02) : 108 - 153
  • [50] Partially connected feedforward neural networks on Apollonian networks
    Wong, W. K.
    Guo, Z. X.
    Leung, S. Y. S.
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2010, 389 (22) : 5298 - 5307
12345