Quantizability and learning complexity in multilayer neural networks

被引:1
|
作者
Fu, LM [1 ]
机构
[1] Univ Florida, Dept Comp & Informat Sci, Gainesville, FL 32611 USA
基金
美国国家科学基金会;
关键词
generalization; learning complexity; machine learning; neural network; quantizability; sample complexity;
D O I
10.1109/5326.669575
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The relationship between quantizability and learning complexity in multilayer neural networks is examined. In a special neural network architecture that calculates node activations according to the certainty factor (CF) model of expert systems, the analysis based upon quantizability leads to lower and also better estimates for generalization dimensionality and sample complexity than those suggested by the multilayer perceptron model. This analysis is further supported by empirical simulation results.
引用
收藏
页码:295 / 300
页数:6
相关论文
共 50 条
  • [31] A Fast Heuristic Global Learning Algorithm for Multilayer Neural Networks
    Siu-yeung Cho
    Tommy W.S. Chow
    Neural Processing Letters, 1999, 9 : 177 - 187
  • [32] Learning shape from focus using multilayer neural networks
    Muhammad, A
    Choi, TS
    VISION GEOMETRY VIII, 1999, 3811 : 366 - 375
  • [33] On optimizing large neural networks (multilayer perceptrons) by learning and evolution
    Braun, H
    ZEITSCHRIFT FUR ANGEWANDTE MATHEMATIK UND MECHANIK, 1996, 76 : 211 - 214
  • [34] Fast Heuristic Global Learning algorithm for multilayer neural networks
    Department of Electronic Engineering, City University of Hong Kong, Hong Kong, Hong Kong
    Neural Process Letters, 2 (177-187):
  • [35] Profiling Student Learning Styles with Multilayer Perceptron Neural Networks
    Latham, Annabel
    Crockett, Keeley
    Mclean, David
    2013 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2013), 2013, : 2510 - 2515
  • [36] Lyapunov stable learning laws for multilayer recurrent neural networks
    Salgado, Ivan
    Guarneros-Sandoval, Alejandro
    Ballesteros, Mariana
    Rodriguez-Santillan, Julia
    Chairez, Isaac
    NEUROCOMPUTING, 2022, 491 : 644 - 657
  • [37] A selective learning algorithm for nonlinear synapses in multilayer neural networks
    Nakayama, K
    Hirano, A
    Fusakawa, M
    IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 1704 - 1709
  • [39] Two-level learning algorithm for multilayer neural networks
    Liu, CS
    Tseng, CH
    TENTH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 1998, : 97 - 102
  • [40] A Pascal program for the Kalman learning algorithm in multilayer neural networks
    Huang, L
    COMPUTERS & GEOSCIENCES, 1997, 23 (08) : 909 - 913