Effective Backpropagation Training with Variable Stepsize

 MAGOULAS George D.
 Department of Electrical and Computer Engineering, University of Patras

 VRAHATIS Michael N.
 Department of Mathematics, University of Patras

 ANDROULAKIS George S.
 Department of Mathematics, University of Patras
Search this Article
Author(s)

 MAGOULAS George D.
 Department of Electrical and Computer Engineering, University of Patras

 VRAHATIS Michael N.
 Department of Mathematics, University of Patras

 ANDROULAKIS George S.
 Department of Mathematics, University of Patras
Journal

 Neural Networks

Neural Networks 10(1), 6982, 19970101
References: 32

1
 Minimization of functions having Lipschitzcontinuous first partial derivatives

ARMIJO L.
Pacific Journal of Mathematics 16, 13, 1966
Cited by (3)

2
 Accelerated backpropagation learning: two optimization methods

BATTITI R.
Complex Systems 3, 331342, 1989
Cited by (2)

3
 <no title>

BRODATZ P.
Textures: A Photographic Album for Artists and Designers, 1966
Cited by (19)

4
 Successfully using peak learning rates of 10 (and greater) in backpropagation networks with the heuristic learning algorithm

CATER J. P.
IEEE First International Conference on Neural Networks 11, 645651, 1987
Cited by (1)

5
 An adaptive training algorithm for backpropagation networks

CHAN L. W.
Computer Speech Language 2, 205218, 1987
Cited by (1)

6
 Note on learning rate schedules for stochastic optimization

DARKEN C.
Advances in neural information processing systems 3, 832838, 1990
Cited by (1)

7
 Towards faster stochastic gradient search

DARKEN C.
Advances in neural information processing systems 4, 10091016, 1991
Cited by (1)

8
 Learning rate schedules for faster stochastic gradient search

DARKEN C.
IEEE Second Workshop on Neural Networks for Signal Processing, 312, 1992
Cited by (1)

9
 <no title>

DEMUTH H.
Neural network toolbox user's guide, 1992
Cited by (3)

10
 Texture classification using the fractal dimension as computed in a wavelet decomposed image

KARAYIANNIS Y. A.
Proceedings of the IEEE Workshop on Nonlinear Signal and Image Processing, 186189, 1995
Cited by (1)

11
 <no title>

MOLER C.
MATLAB user's guide, 1987
Cited by (1)

12
 Improving the learning speed of 2layer neural networks by choosing initial values of the adaptive weights

NGUYEN D.
IEEE First International Joint Conference on Neural Networks 3, 2126, 1990
Cited by (1)

13
 <no title>

RUMELHART D. E.
Parallel distributed processing, 1986
Cited by (122)

14
 Accelerating the convergence of the backpropagation method

VOGL T. P.
Biological Cybernetics vol.59, 257263, 1988
Cited by (13)

15
 Neural networks and principal component analysis

BALDI P.
Neural Networks 2, 5358, 1989
Cited by (36)

16
 Enhanced training algorithms, and integrated training/architecture selection for multilayer perceptron networks.

BELLO M. G.
IEEE Transactions on Neural Networks 3, 864875, 1992
Cited by (4)

17
 Approximation of boolean functions by sigmoidal networks: Part I: XOR and other twovariable functions.

BLUM E. K.
Neural Computation 1, 532540, 1989
DOI Cited by (4)

18
 Backpropagation learning and nonidealities in analog neural network hardware

FRYE R. C.
IEEE Trans. Neural Networks 2(1), 110117, 1991
Cited by (5)

19
 Cauchy's method of minimization

GOLDSTEIN A. A.
Numerische Mathematik 4, 146150, 1962
DOI Cited by (1)

20
 Statistical and Structural Approaches to Texture

HARALICK R. M.
Proc. IEEE 67(5), 786804, 1979
DOI Cited by (29)

21
 Finite precision error analysis of neural network hardware implementations

HOLT J. L.
IEEE Transactions on Computers 3, 281290, 1993
Cited by (1)

22
 Increased Rates of Convergence Through Learning Rate Adaptation

JACOBS R. A.
Neural Networks 1, 295307, 1988
Cited by (63)

23
 An adaptive least squares algorithms for the efficient training of artificial neural networks

KOLLIAS S.
IEEE Trans. Circuits & Syst. 36, 8, 10921101, 1989
Cited by (4)

24
 An analysis of premature saturation in back propagation learning.

LEE Y.
Neural Networks 6, 719728, 1993
Cited by (3)

25
 Characterization of Signals from Multiscale Edges

MALLAT S.
Trans. IEEE 14(7), 1992
DOI Cited by (96)

26
 Fractal  based description of natural scenes

PENTLAND A. P.
IEEE Transactions on Pattern Analysis and Machine Intelligence 6(6), 661674, 1984
Cited by (55)

27
 Reduction of required precision bits for backpropagation applied to pattern recognition

SAKAUE S.
IEEE Trans. Neural Netw. 4(2), 270275, 1993
Cited by (2)

28
 Acceleration techniques for the backpropagation algorithm

SILVA F.
Lecture Notes in Computer Science 412, 110119, 1990
Cited by (2)

29
 Speed Up Learning and Network Optimization with Exteded Back Propagation

SPERDUTI A.
Neural Networks 6, 365383, 1993
Cited by (6)

30
 Minimization Methods for Training Feedforward Neural Network

VAN DER SMAGT P. P.
Neural Networks 7(1), 111, 1994
Cited by (7)

31
 Improving the convergence of the backpropagation algorithm

van OOYEN A.
Neural Networks 5(3), 465471, 1992
Cited by (29)

32
 A method for self determination of adaptive learning rates in back propagation

WEIR M. K.
Neural Networks 4, 371379, 1991
Cited by (6)
Cited by: 2

1
 Introduction of Orthogonal Transform into Multilayered Neural Filter [in Japanese]

NAKANISHI Isao , ITOH Yoshio , FUKUI Yutaka
Technical report of IEICE. DSP 98(451), 7178, 19981211
References (15)

2
 New training strategies for constructive neural networks with application to regression problems

MA L. , KHORASANI K.
Neural Networks 17(4), 589609, 200405
References (36) Cited by (2)