An efficient MDLbased construction of RBF networks

 LEONARDIS Ales
 Faculty of Computer and Information Science, University of Ljubljana

 BISCHOF Horst
 Pattern Recognition and Image Processing Group, Vienna University of Technology
Search this Article
Author(s)

 LEONARDIS Ales
 Faculty of Computer and Information Science, University of Ljubljana

 BISCHOF Horst
 Pattern Recognition and Image Processing Group, Vienna University of Technology
Journal

 Neural Networks

Neural Networks 11(5), 963973, 19980701
References: 44

1
 Information and an extension of the maximum likelihood principle

AKAIKE H.
2nd International Symposion on Information Theory, 267281, 1973
Cited by (1)

2
 <no title>

CICHOCKI A.
Neural networks for optimization and signal processing, 1993
Cited by (25)

3
 The cascadecorrelation learning architecture

FAHLMAN S. E.
Advances in Neural Information Processing Systems 2, 524532, 1990
Cited by (15)

4
 Objective functions for feature discrimination

FUA P.
Processing of the 11th Internasional Joint Conference on Artificial Intelligence, 15961602, 1989
Cited by (1)

5
 Tabu search

GLOVER F.
Modern Heuristic Techniques for Combinatorial Problems, 70150, 1993
Cited by (1)

6
 Second order derivatives for network pruning: optimal brain surgeon

HASSIBI B.
NIPS 5, 164172, 1993
Cited by (1)

7
 <no title>

HAYKIN S.
Neural NetworksA Comprehensive Foundation, 1994
Cited by (67)

8
 Optimal brain damage

LE CUN Y. L.
Advances in Neural Information Processing Systems 2, 598605, 1988
Cited by (1)

9
 Dealing with occlusions in the eigenspace approach

LEONARDIS A.
Proc. of CVPR96, 453458, 1996
Cited by (1)

10
 Adaptive radial basis function nanlinearities, and the problem of generalization

LOWE D. G.
1st IEE Conference on Artificial Neural Networks, 171175, 1989
Cited by (1)

11
 The effective number of parameters : an analysis of generalization and regularization in nonlinear learning systems

MOODY J. E.
Advances in Neural Information Processing Systems 4, 847854, 1992
Cited by (5)

12
 Skeletonization : A technique for trimming the fat from a network via relevance assessment

MOZER M. C.
Advances in neural information processing systems 1, 107115, 1989
Cited by (3)

13
 <no title>

RISSANEN J.
Stochastic Complexity in Statistical Inquity, Series in Computer Science 15, 1989
Cited by (1)

14
 Complexity analysis of RBF networks for pattern recognition

SARDO L.
Proceedings of the CVPR'96, 574579, 1996
Cited by (1)

15
 A mathematical theory of communication

SHANNON C.
Bell Systems Technical Journal 27, 379423, 1948
Cited by (1)

16
 Crossvalidatory choice and assessment of statistical predictions

STONE M.
Journal of the Royal Statistical Society B 36(1), 111147, 1974
Cited by (1)

17
 <no title>

VAPNIK V. N.
Estimation of Dependences Basad on Empirical Data, 1982
Cited by (1)

18
 Finding optimal neural networks for land use classification

BISCHOF H.
IEEE Transactions on Geoscience and Remote Sensing 36(1), 337341, 1998
Cited by (1)

19
 Curvaturedriven smoothing : A learning algorithm for feedforward networks

BISHOP C. M.
IEEE Trans. Neural Netw. 4(5), 882884, 1993
Cited by (6)

20
 Training with noise is equivalent to Tikhonov regularization

BISHOP C. M.
Neural Computation 7(1), 108116, 1995
Cited by (8)

21
 A robust back propagation learning algorithm for function approximation

D. S. Chen
IEEE Trans. Neural Netw. 5(3), 467479, 1994
DOI Cited by (9)

22
 Fast learning with incremental RBF networks

FRITZKE B.
Neural Processing Letters 1(2), 5, 1994
DOI Cited by (5)

23
 Regularization Theory and Neural Networks Architectures

GIROSI F.
Neural Comp., 219269, 1995
Cited by (23)

24
 Connectionist learning procedures

HINTON G. E.
Artificial Intelligence 40, 185234, 1989
Cited by (20)

25
 Flat minima

HOCHREITER S.
Neural Computation 9(1), 143, 1997
DOI Cited by (2)

26
 Constructing simple stable descriptions for image partitioning

LECLERC Y. G.
Int. J. Comput. Vision 3(1), 73102, 1989
Cited by (20)

27
 Segmentation of range images as the search for geometric parametric models

LEONARDIS A.
International Journal of Computer Vision 14(3), 253277, 1995
Cited by (1)

28
 Robust error measure for supervised neural network learning with outliers

LIANO K.
IEEE Transactions on Neural Networks 7(1), 246250, 1996
Cited by (5)

29
 Bayesian interpolation

MACKAY D. J. C.
Neural Computation 4(3), 415447, 1992
DOI Cited by (62)

30
 A practical Bayesian framework for backpropagation networks

MACKAY D. J. C.
Neural Computation 4, 448472, 1992
DOI Cited by (37)

31
 Fast learning in networks of locallytuned processing units

MOODY J.
Neural Computation 1(2), 281294, 1989
DOI Cited by (121)

32
 Simplifying neural networks by soft weightsharing

NOWLAN S. J.
Neural Computation 4, 473493, 1992
DOI Cited by (16)

33
 Regularization in the Selection of Radial Basis Function Centers

ORR M. J. L.
Neural Computation 7, 606623, 1995
Cited by (6)

34
 Automatic Extraction of Deformable Part Models

PENTLAND A. P.
International Journal of Computer Vision 4, 107126, 1990
Cited by (13)

35
 A resource allocating network for function interpolation

PLATT J.
Neural Computation 3(2), 213225, 1991
DOI Cited by (40)

36
 Networks for approximation and learning

POGGIO T.
Proc. IEEE 78(9), 14811497, 1990
DOI Cited by (166)

37
 A Universal Prior for Integers and Estimation by Minimum Description Length

RISSANEN J.
Ann. Statist 11, 416431, 1983
DOI Cited by (61)

38
 Universal coding, information, prediction and estimation

RISSANEN J.
IEEE Trans. Inf. Theory 30(4), 629636, 1984
DOI Cited by (98)

39
 An Algorithm to Generate Radial Basis Function (RBF)Like Nets for Classification Problems

ROY Asim , GOVIL Sandeep , MIRANDA Raymond
Neural Networks 8(2), 179201, 19950301
DOI References (33) Cited by (4)

40
 ExSel + + : a general framework to extract parametric models

STRICKER M.
6th CAIP'95, number 970 in Lecture Notes in Computer Science, 9097, 1995
Cited by (1)

41
 Predicting the future: A connectionist approach

WEIGEND A. S.
Int. J. of Neural Systems 1(3), 193209, 1990
DOI Cited by (8)

42
 Evolving space filling curves to distribute radial basis function networks over an input space

WHITEHEAD B. A.
IEEE Transactions on Neural Networks 5(1), 1523, 1994
Cited by (3)

43
 A sequential learning scheme for function approximation using minimal radial basis function neural networks

YINGWEI L.
Neural Computation 9, 461478, 1997
DOI Cited by (19)

44
 Learning population codes by minimum description length

ZEMEL R. S.
Neural Computation 7(3), 549564, 1995
Cited by (1)
Cited by: 5

1
 Iterative fast orthogonal search algorithm for MDLbased training of generalized singlelayer networks

ADENEY K. M. , KORENBERG M. J.
Neural networks : the official journal of the International Neural Network Society 13(7), 787799, 20000901
References (35)

2
 Comparative Study on Adaptive State Space Construction Methods for Reinforcement Learning using RBF Neural Network [in Japanese]

OHTANI Yoshihiro , MURAO Hajime , TAMAKI Hisashi , KITAMURA Shinzo
自律分散システム・シンポジウム資料 = SICE Symposium on Decentralized Autonomous Systems 14, 159163, 20020125
References (3)

3
 Structural Optimization by Genetic Algorithm with degeneration (GA^d) [in Japanese]

TAKAHAMA Tetsuyuki , SAKAI Setsuko , ICHIMURA Takumi , ISOMICHI Yoshinori
The Transactions of the Institute of Electronics,Information and Communication Engineers. 86(3), 140149, 20030301
IR References (22) Cited by (1)

4
 A Study on Adaptive Control of Degeneration Speed in Structural Learning of Fuzzy Rules by Genetic Algorithms with Degeneration GA^d [in Japanese]

TAKAHAMA Tetsuyuki , SAKAI Setsuko , ISOMICHI Yoshinori
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 16(1), 3343, 2004
JSTAGE References (28)

5
 MGGA : Genetic Algoreithm with Mutant Genes [in Japanese]

TAKAHAMA Tetsuyuki , SAKAI Setsuko , ISOMICHI Yoshinori
The Transactions of the Institute of Electronics,Information and Communication Engineers. 00084(00009), 12971306, 20010901
IR References (25) Cited by (2)