The constraint based decomposition (CBD) training architecture

 DRAGHICI Sorin
 431 State Hall, Department of Computer Science, Wayne State University
Search this Article
Author(s)

 DRAGHICI Sorin
 431 State Hall, Department of Computer Science, Wayne State University
Journal

 Neural Networks

Neural Networks 14(4), 527550, 20010501
References: 82

1
 <no title>

BENNETT K. P.
Geometry at work, 1998
Cited by (1)

2
 <no title>

BLAKE C.
UCI Repository of machine learning databases, 1998
Cited by (10)

3
 <no title>

BORSUK K.
Multidimensional analytic geometry, 1969
Cited by (1)

4
 Gradient descent fails to separate

BRADY M.
Proceedings of the IEEE International Conference on Neural Networks 1, 649656, 1988
Cited by (1)

5
 <no title>

BREIMAN L.
Classification and Regression Trees, 1984
Cited by (111)

6
 Multivariable functional interpolation and adaptive networks

BROOMHEAD D. S.
Complex Systems 2, 321323, 1988
Cited by (1)

7
 The constraint based decomposition training architecture

DRAGHICI S.
Proceedings of World Congress on Neural Networks 3, 545555, 1994
Cited by (1)

8
 <no title>

DRAGHICI S.
Using constraints to improve generalization and training of feedforward neural networks: constraint based decomposition and comp, 1995
Cited by (1)

9
 A VLSI optimal constructive algorithm for classification problems

DRAGHICI S.
Smart engineering systems: neural networks, fuzzy logic, data mining and evolutionary programming, 141151, 1997
Cited by (2)

10
 Comparative study of publicdomain supervised machinelearning accuracy on the UCI database

EKLUND P. W.
Proceedings of the data mining and knowledge discovery: theory, tools and technology, 3950, 2000
Cited by (1)

11
 The recurrent cascadecorrelation architecture

FAHLMAN S. E.
Advances in neural information processing systems 3, 190196, 1991
Cited by (1)

12
 <no title>

FAHLMAN S. E.
The cascadecorrelation learning architecture, 1990
Cited by (3)

13
 Comparative bibliography of ontogenetic neural networks

FIESLER E.
Proceedings of the International Conference on Neural Networks (ICANN '94), 793796, 1994
Cited by (1)

14
 <no title>

FIESLER E.
Handbook of neural computation, 1996
Cited by (2)

15
 Optimal linear discriminants

GALLANT S. I.
Eighth International Conference on Pattern Recognition, 849852, 1986
Cited by (1)

16
 Induction of oblique decision tree

HEATH S. K. D.
IJCAI93, 1993
Cited by (1)

17
 Weight freezing in constructive neural networks: a novel approach

HOSSEINI S.
Lecture notes in computer science: engineering applications of bioinspired artificial neural networks, 1607,101607,20, 1999
Cited by (1)

18
 Learning vector quantization

KOHONEN T.
The handbook of brain theory and neural networks, 537540, 1995
Cited by (2)

19
 Learninig to tell two spirals apart

LANG K. J.
Proceedings of the 1988 Connectionist Models Summer School, 5261, 1989
Cited by (1)

20
 Version spaces: a candidate elimination approach to rule learning

MITCHELL T. M.
IJCAI 1, 11391151, 1977
Cited by (1)

21
 OCI: randomized induction of oblique decision trees

MURTHY S. K.
Proceedings of the Eleventh National Conference on Artificial Intelligence, 322327, 1993
Cited by (1)

22
 <no title>

PAREKH R. G.
Constructive neural network learning algorithms for multicategory pattern classification (Postscript), 1995
Cited by (1)

23
 Classification using Φmachines and constructive function approximation

PRECUP D.
Proc. 15th International Conference on Machine Learning, 439444, 1998
Cited by (1)

24
 <no title>

PREPARATA F. P.
Computational Geometry : An Introduction, 1985
Cited by (38)

25
 A toolbox for analysis and visualization of sensor data in supervision

RAUBER T. W.
Proceedings of International Conference of Fault Diagnosis, 1993
Cited by (1)

26
 Learning by minimizing resources in neural networks

RUJAN P.
Complex Systems 3, 229241, 1989
Cited by (1)

27
 Comparison between entropy nets and decision tree classifiers

SETHI I.
International Joint Conference on Neural Networks 3, 4146, 1990
Cited by (1)

28
 A constructive cascade network with adaptive regularization to appear as Lecture Notes in Computer Science

TREADGOLD N. K.
Proceedings of IWANN'99, 4049, 1999
Cited by (1)

29
 <no title>

UTGOFF P. E.
Linear machine decision trees, 1991
Cited by (1)

30
 <no title>

UTGOFF P. E.
Constructive function approximation, 1997
Cited by (1)

31
 Constructive function approximation

UTGOFF P. E.
Feature extraction, construction and selection: a data mining perspective 453, 1998
Cited by (1)

32
 DistAI: an interpattern distancebased constructive learning algorithm

YANG J.
World Congress on Computational Intelligence, 22082213, 1998
Cited by (1)

33
 ELEM2: a learning system for more accurate classifications

AN A.
Lecture notes in artificial intelligence 1418, 426441, 1998
Cited by (1)

34
 Growing layers of perceptrons : Introducing the Extentron algorithm

BAFFES P. T.
Proc. of Int. Joint Conf. Neural Networks, Baltimore II, 392397, 1992
Cited by (3)

35
 The patch algorithm: Fast design of binary feedforward neural network

BARKEMA G. T.
Network. I, 393407, 1993
DOI Cited by (2)

36
 Tilinglike learning in the parity machine

BIEHL M.
Physical Review A 44(10), 68886894, 1991
Cited by (1)

37
 Novelty detection and neural network validation

BISHOP C. M.
IEE Proc. Vision, Image and Signal Processing 141(4), 217222, 1994
Cited by (4)

38
 Backpropagation fails to separate where perceptrons succeed

BRADY M. L.
IEEE Transactions on Circuits and Systems 36, 665674, 1989
Cited by (4)

39
 Storage capacity of a constructive learning algorithm

BUHOT A.
Journal of Physics AMathematical and General 33(9), 17131727, 2000
DOI Cited by (1)

40
 The target switch algorithm: a constructive learning procedure for feedforward neural networks [Letter]

CAMPBELL C.
Neural Computation 7(6), 12451264, 1995
DOI Cited by (2)

41
 The CN2 induction algorithm

CLARK P.
Machine Learning 3,4, 261284, 1989
DOI Cited by (18)

42
 Three algorithms for estimating the domain of validity of feedforward neural networks

COURRIEU P.
Neural Networks 7, 169174, 1994
Cited by (2)

43
 Enhancement of the constraint based decomposition training architecture

DRAGHICI S.
Proceedings of IEEE International Conference on Neural Networks IJCNN '96 1, 317322, 1996
Cited by (1)

44
 On the complexitycapability relationship of adaptive systems based on VLSI friendly neural networks

DRAGHICI S.
Lecture notes in artificial intelligence, Proceedings of XII Canadian Conference on Artificial Intelligence AI'98 1418, 285297, 1998
Cited by (1)

45
 Cascade error projection : A learning algorithm for hardware implementation

DUONG T. A.
Foundations and tools for neural modeling, lecture notes in computer science, 450457, 1999
Cited by (2)

46
 A constructive algorithm for binary neural networks : The oilspot algorithm

FRATTALEMASCIOLI F. M.
IEEE Trans. Neural Networks 6(3), 794797, 1995
Cited by (4)

47
 The upstart algorithm: A method for consructing and training feedforward neural networks

FREAN M.
Neural Computation 2, 198209, 1990
DOI Cited by (9)

48
 The Cascadecorrelation Learning : A Projection Pursuit Learning Perspective

HWANG JenqNeng
IEEE Trans. on Neural Networks 7(2), 278289, 1996
Cited by (4)

49
 Learning with limited numerical precision using the cascadecorrelation algorithm

HOHFELD M.
IEEE Transactions on Neural Networks 3(4), 602611, 1992
Cited by (4)

50
 "Big Omicron and big Omega and big Theta", SIGACT News

KNUTH D. E.
Special Interest Group on Algorithms and Computation Theory 8, 1814, 1976
DOI Cited by (3)

51
 Learning vector quantization

KOHONEN T.
Neural Networks 1(Suppl. 1), 303, 1988
DOI Cited by (1)

52
 Constructive algorithms for structure learning in feedforward neural networks for regression problems

KWOK T.Y.
IEEE Trans. Neural Networks 8(3), 630645, 1997
Cited by (9)

53
 Moderating the outputs of support vector machine classifiers

KWOK T.
IEEE Tran. on Neural Networks 8, 11311148, 1999
Cited by (7)

54
 Fast initialization for cascadecorrelation learning[Brief paper]

LEHTOKANGAS M.
IEEENN 10(2), 410, 1999
Cited by (1)

55
 Improvement of cascade correlation learning algorithm with an evolutionary initialization

LIANG H.
Information Sciences 112(14), 16, 1998
DOI Cited by (1)

56
 A convergence theorem for sequential learning in twolayer perceptrons

MARCHAND M.
Europhysics Letters 11(6), 487492, 1990
Cited by (2)

57
 Learning in feedforward layered network: The tiling algorithm

MEZARD J.
J. Phys. A: Math. Gen. 22, 21912203, 1989
Cited by (11)

58
 Fast learning in networks of locallytuned processing units

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

59
 On the training of radial basis function classifiers

MUSAVI M. T.
Neural Networks 5, 595603, 1922
Cited by (26)

60
 On sequential construction of binary neural networks

MUSELLI M.
IEEE Trans. Neural Networks 6(3), 678690, 1995
Cited by (14)

61
 Constructive neuralnetwork learning algorithms for pattern classification

PAREKH R.
IEEE Transactions on Neural Networks 11(2), 436, 2000
Cited by (1)

62
 Networks for approximation and learning

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

63
 Investigation of the cascor family of learning algorithms

PRECHELT L.
Neural Networks 10(5), 885896, 1997
DOI Cited by (3)

64
 <no title>

QUINLAN J. R.
C4.5: Programs for machine learning, 1993
Cited by (217)

65
 Divide and Conquer Neural Network

ROMANIUK S. T.
Neural Networks 6, 8, 11051116, 1993
Cited by (3)

66
 <no title>

I. K. Sethi
Proc. IEEE 78, 1605, 1990
Cited by (11)

67
 <no title>

SIETSMA J.
Neural Networks 4, 6779, 1991
DOI Cited by (40)

68
 Neural trees : A new tool for classification

SIRAT J. A.
Network 1, 423448, 1990
DOI Cited by (4)

69
 Neural network constructive algorithms: trading generalization for learning efficiency?

SMIEJA F. J.
Circuits Systems Signal Processing 12(2), 331374, 1993
Cited by (2)

70
 Parallelizing the cascadecorrelation algorithm using time warp

SPRINGER P. L.
Neural Networks 8(4), 571577, 1995
DOI Cited by (1)

71
 Cascade ARTMAP : Integrating neural computation and symboli knowledge processing

TAN AH.
IEEE Transactions on Neural Networks 8(2), 237250, 1997
Cited by (4)

72
 An efficient partition of training data set improves speed and accuracy of cascadecorrelation algorithm

TETKO I. V.
Neural Processing Letters 6(1/2), 5159, 1997
DOI Cited by (1)

73
 An enhancement of generalization ability in cascade correlation algorithm by avoidance of overfitting/overtraining problem

TETKO I. V.
Neural Processing Letters 6(1/2), 4350, 1997
DOI Cited by (1)

74
 Two neural network construction methods

THIMM G.
Neural Processing Letters 6(1/2), 2531, 1997
DOI Cited by (1)

75
 Extending and benchmarking the CasPer algorithm

TREADGOLD N. K.
Proceedings of the 10th Australian Joint Conference on Artificial Intelligence: Advanced Topics in Artificial Intelligence (AI9 1342, 398406, 1997
Cited by (1)

76
 Constructing higher order neurons of increasing complexity in cascade networks

TREADGOLD N. K.
Lecture Notes in Computer Science 1416, 557563, 1998
Cited by (1)

77
 Exploring constructive cascade networks

TREADGOLD N. K.
IEEE Transactions on Neural Networks 10(6), 13351350, 1999
Cited by (3)

78
 Incremental Induction of Decision Trees

UTGOFF P. E.
Machine Learning Vol.4, 161186, 1989
DOI Cited by (9)

79
 Decision tree induction based on efficient tree restructuring

UTGOFF P. E.
Machine Learning 29(1), 544, 1997
DOI Cited by (2)

80
 Datadriven theory refinement using KBDistAI

YANG J.
Lecture Notes in Computer Science 1642, 331342, 1999
Cited by (1)

81
 CARVE : A constructive algorithm for realvalued examples

YOUNG S.
IEEE Trans. Neural Networks 9(6), 11801190, 1998
Cited by (3)

82
 Dynamic Constructive Fault Tolerant Algorithm for Feedforward Neural Networks

HAMMADI Nait Charif , OHMAMEUDA Toshiaki , KANEKO Keiichi , ITO Hideo
IEICE Transactions on Information and Systems 81(1), 115123, 19980125
References (18) Cited by (6)
Cited by: 1

1
 On the capabilities of neural networks using limited precision weights

DRAGHICI Sorin
Neural networks : the official journal of the International Neural Network Society 15(3), 395414, 20020401
References (140)