FANG Jian, XI Yugeng. A RECENT SURVEY OF NEURAL NETWORK ARCHITECTURE DESIGN[J]. INFORMATION AND CONTROL, 1996, 25(3): 156-164.
Citation: FANG Jian, XI Yugeng. A RECENT SURVEY OF NEURAL NETWORK ARCHITECTURE DESIGN[J]. INFORMATION AND CONTROL, 1996, 25(3): 156-164.

A RECENT SURVEY OF NEURAL NETWORK ARCHITECTURE DESIGN

More Information
  • Received Date: August 07, 1995
  • Revised Date: March 27, 1996
  • Published Date: June 19, 1996
  • Designing neural network architecture is an interesting and tough task,this paper reviews recent researches in this area.First we analysis four criteria while designing neural network topology:minimizing the function approximation error,complexity,generalization and fault tolerance.After that,we give a detailed discussion of three designing methods,namely constructive algorithms,destructive algorithms and evolutionary algorithms.Finally suggestions for further research are presented.
  • [1]
    Wang Zhenni,Tham Ming T,Morris A Julian.Multilayer Feedforward Neural Networks:A Canonical form Approximation of Nonlinearity.Int J Control,1992,56(3):655~672
    [2]
    Barronr Andrew R.Approximation and Estimation Bounds for Artificial Neural Networks.Machine Learning,1994,14:115-133
    [3]
    Billings S A,Jamaluddin H B.Chen S.Properties of Neural Networks with Applications to Modelling Non-Linear Dynamical Systems.Int J Control,1992,55(1):193-224
    [4]
    Levin Esther,Tishiby Naftali,Solia Sara A.A Statistical Approach to Learning and Generalization in Layered Neural Networks.Proceedings of the IEEE,1990,78(10):1568-1574
    [5]
    Fogel David B.An Information Criterion for Optimal Neural Network Selection.IEEE Trans on Neural Networks,1991,2(5):490-497
    [6]
    Murata N,Yoshizawa S,Amari S.Network Information Criterion-Determining the Number of Hidden Units for an Artificial Neural Network Model.IEEE Trans on Neural Netwroks,1994,5(6):865-872
    [7]
    Neti C,Schneider M H,Young E D.Maximally Fault Tolerant Neural Networks,IEEE Trans on Neural Networks,1992,3(1):14-23
    [8]
    Wang Zhenni,Massimo Christine Di,Tham Ming T,Morris A Julian.A Procedure for Determining the Topology of Multilayer Feedforward Neural Networks.Neural Networks,1994,7(2):291-300
    [9]
    Azimi-Sadjadi M R,Sheedvash S.Trujillo F O.Recursive Dynamic Node Creation in Multilayer Neural Networks.IEEE Trans on Neural Networks.1993,4(2):242-256
    [10]
    Bartlett Eric B.Dynamic Node Architecture Learning:An Information Theoretic Approach.Neural Networks,1994,7(1):129-140
    [11]
    Tarek M N,Albert Y Z.Toward Generating Neural Networks Structures for Function Approximation.Neural Net-works,1994,71:89-99
    [12]
    Happle Bart L M.Murre Jacob M.Design and Evoluation of Modular Neural Network Architectures.Neural Net-works,1994,7(6/7),985-1004
    [13]
    Cios K J.Liu N.A Machine Learning Method for Generation of a Neural Network Architecture,A Continuous ID3 Algorithm.IEEE Trans on Neural Networks.1992,3(2):280-291
    [14]
    Omidvar O M,Wilson C L.Optimization of Neural Network Topology and Information Content Using Boltzmann Methods.IEEE IJCNNS.1992,4:594-599
    [15]
    Kruschke John K.Imporving Generalization in Back-Propagation Networks with Distributed Bottleneck.IEEE INNS IJCNNS,1989,1:443-448
    [16]
    Russell Reed,Pruning Algorithms-A Survey.IEEE Trans on Neural Networks.1993,4(5):740-747
    [17]
    Fogel D B,Fogel L J.Porto V W.Evolving Neural Networks.Biol Cybern,1990,63:487-493
    [18]
    Yao Xin.A Review of Evolutionary Artificial Neural Networks.Int J Intelligent Systems,1993.8:539-567
    [19]
    Whitley D.Starkweather T,Bogart C.Genetic Algorithms and Neural Networks:Optimizing Connections and Connectivity,Parallel Computing.1990.14,347-361
    [20]
    Angeline Peter J,Saunders Gregory M,Pollack Jordan B.An Evolutionary Algorithm that Constructs Recurrent Neural Networks.IEEE Trans on Neural Networks,1994,5(1):54-65

Catalog

    Article views (778) PDF downloads (401) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return