A modified backpropagation method to avoid false local minima

 FUKUOKA Yutaka
 Institute for Medical and Dental Engineering, Tokyo Medical and Dental University

 MATSUKI Hideo
 Faculty of Science and Technology, Keio University

 MINAMITANI Haruyuki
 Faculty of Science and Technology, Keio University

 ISHIDA Akimasa
 Institute for Medical and Dental Engineering, Tokyo Medical and Dental University
Search this Article
Author(s)

 FUKUOKA Yutaka
 Institute for Medical and Dental Engineering, Tokyo Medical and Dental University

 MATSUKI Hideo
 Faculty of Science and Technology, Keio University

 MINAMITANI Haruyuki
 Faculty of Science and Technology, Keio University

 ISHIDA Akimasa
 Institute for Medical and Dental Engineering, Tokyo Medical and Dental University
Journal

 Neural Networks

Neural Networks 11(6), 10591072, 19980801
References: 31

1
 Improving the learning rate of backpropagation with the gradient reuse algorithm.

HUSH D. R.
Proceedings of the IEEE Conference on Neural Networks I, 441447, 1988
Cited by (1)

2
 Capabilities of threelayered perceptions.

IRIE B.
Proceedings of the IEEE Conference on Neural Networks I, 641648, 1988
Cited by (1)

3
 Back propagation is sensitive to initial conditions.

KOLEN J. F.
Advances in Neural Information Processing Systems 3, 860867, 1991
Cited by (1)

4
 Efficient parallel learning algorithms for neural networks.

KRAMER A. H.
Advances in Neural Information Processing Systems, 4048, 1989
Cited by (1)

5
 Classification of large set of handwritten characters using modified back propagation model.

KRZYZAK A.
Proceedings of the International Joint Conference on Neural Networks III, 225232, 1990
Cited by (1)

6
 An algebraic projection analysis for optimal hidden units size and learning rates in backpropagation learning.

KUNG S. Y.
Proceedings of the IEEE Conference on Neural Networks I, 363370, 1988
Cited by (1)

7
 Back propagation error surfaces can have local minima.

MCINERNEY J. M.
Proceedings of the International Joint Conference on Neural Networks II, 627, 1989
Cited by (1)

8
 Improving the learning speed of 2layer neural networks by choosing initial values of the adaptive weights.

NGUYEN D.
Proceedings of the International Joint Conference on Neural Networks III, 2126, 1990
Cited by (1)

9
 Optimal algorithms for adaptive networks: second order back propagation, second order direct propagation, and second order Hebbian learning

PARKER D. B.
Proceedings of the IEEE Conference on Neural Networks II, 593600, 1987
Cited by (1)

10
 A mean field theory learning algorithm for neural networks

PETERSON C.
Complex Systems 1, 9951019, 1987
Cited by (10)

11
 The effect of the slope of the activation function on the back propagation algorithm.

REZGUI A.
Proceedings of the International Joint Conference on Neural Networks I, 707710, 1990
Cited by (1)

12
 Accelerating the convergence of the backpropagation method

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

13
 Learning algorithms for connectionist networks: applied gradient methods of nonlinear optimization.

WATROUS R. L.
Proceedings of the IEEE Conference on Neural Networks II, 619627, 1987
Cited by (1)

14
 Recent advances on techniques of static feedforward networks with supervised learning.

XU L.
International Journal of Neural Systems 3, 253290, 1992
Cited by (1)

15
 Mean field annealing : a formalism for constructing GNClike algorithms

BILBRO G. L.
IEEE Trans. Neural Networks 3, 131138, 1992
Cited by (10)

16
 Approximation by superpositions of a sigmoidal function

CYBENKO G.
Mathematics of Control, Signals and Systems 2, 303314, 1989
DOI Cited by (93)

17
 <no title>

FUNAHASHI K.
On the Approximate Realization of Continuous Mapping by Neural Networks 2, 183192, 1989
DOI Cited by (203)

18
 Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images

GEMAN S.
IEEE Trans. Patt. Anal. & Mach. Intell. PAMI6, 721741, 1984
Cited by (361)

19
 Multilayer feedforward neural networks are universal approximators

HORNIK K.
Neural Networks 25, 359366, 1989
DOI Cited by (135)

20
 Progress in Supervised Neural Network

HUSH D. R.
IEEE Signal Processing Magazine, 839, 1993
Cited by (13)

21
 Error Surface for Multilayer Perceptrons

HUSH D. R.
IEEE Trans. Syst. Man and Cybern. 22(5), 11521161, 1992
Cited by (4)

22
 Increased Rates of Convergence Through Learning Rate Adaptation

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

23
 Optimization by Simulated Annealing

KIRKPATRICK S.
Science 220, 671680, 1983
DOI Cited by (557)

24
 Paralleled hardware annealing for optimal solutions on electronic neural networks

LEE B. W.
IEEE Trans. Neural Networks 4(4), 588599, 1993
Cited by (3)

25
 An analysis of premature saturation in back propagation learning.

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

26
 Rescaling of variables in back propagation learning.

RIGLER A. K.
Neural Networks 4, 225229, 1991
Cited by (3)

27
 Learning representations by backpropagation errors

RUMMELHART D. E.
Nature 323, 533536, 1986
DOI Cited by (400)

28
 Improving the convergence of the backpropagation algorithm

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

29
 A method for self determination of adaptive learning rates in back propagation

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

30
 Avoiding false local minima by proper initialization

WESSELS L. F. A.
IEEE Trans. Neural Networks 3(6), 899905, 1992
Cited by (4)

31
 Handwritten Numeral Recognition by Multilayered Neural network with Improved Learning Algorithm

YAMADA K.
Proc. of Int. Joint Conf. on Neural Network, 1989, 1989
Cited by (4)
Cited by: 3

1
 Construction of Decision System for the Appropriate Seat Height using NeuralNetwork [in Japanese]

KISHI Shinsuke , MITSUYA Reiko , NORO Kageyu
ヒューマンインタフェース学会論文誌 8(1), 151156, 20060225
References (15)

2
 A New Approach to the Structural Learning of Neural Networks

DEBNATH Rameswar , TAKAHASHI Haruhisa
IEICE transactions on fundamentals of electronics, communications and computer sciences 87(6), 16551658, 20040601
References (12)

3
 A Video Summarization Method Based on the Film Grammar and Subjective Rating [in Japanese]

NI Chanbin , NOMURA Toshio , WATANABE Shuichi , OKADA Hiroyuki , KAMEYAMA Wataru
IPSJ SIG Notes 56, 1318, 20070305
References (9)