Accelerating neural network training using weight extrapolations

 KAMARTHI S. V.
 Department of Mechanical, Industrial and Manufacturing Engineering, Northeastern University

 PITTNER S.
 Department of Mechanical, Industrial and Manufacturing Engineering, Northeastern University
Search this Article
Author(s)

 KAMARTHI S. V.
 Department of Mechanical, Industrial and Manufacturing Engineering, Northeastern University

 PITTNER S.
 Department of Mechanical, Industrial and Manufacturing Engineering, Northeastern University
Journal

 Neural Networks

Neural Networks 12(9), 12851299, 19991101
References: 50

1
 Improving convergence of back propagation by handling flatspots in the output layer

BALAKRISHNAN K.
Artificial neural network 2, 10031009, 1992
Cited by (1)

2
 Constructing hidden units using examples and queries

BAUM E. B.
Advances in neural information processing systems 3, 904910, 1991
Cited by (1)

3
 <no title>

BAZARAA M. S.
Nonlinear Programming Theory and Algorithms, 1993
Cited by (13)

4
 <no title>

BISHOP C. M.
Neural Networks for Pattern Recognition, 1995
Cited by (116)

5
 <no title>

BRENT R. P.
Alsorithms for minimization withzout derivatives, 1973
Cited by (1)

6
 Successfully usinn peak learning rates of 10 (and greater) in backpropagation networks with the heuristic learning algorithm

CATER J. P.
Proceedings of the IEEE International Conference on Neural Networks 2, 645651, 1987
Cited by (1)

7
 An accelerated learning method with backpropagation

CHO S. B.
Proceedings of the International Joint Conference on Neural Networks 1, 605608, 1990
Cited by (1)

8
 Accelerated learning using the generalized delta rule

DAHL E. D.
Proceedings of the IEEE International Conference on Neural Networks 2, 523530, 1987
Cited by (1)

9
 <no title>

DENNIS J. E.
Numerical Methods for Unconstrained Optimization and Nonlinear Equations, 1983
Cited by (6)

10
 Extrapolatory methods for speeding up the BP algorithm

DEWAN H. M.
Proceedings of the International Joint Conference on Neural Networks 1, 613616, 1990
Cited by (1)

11
 Fasterlearning variations on backpropagation: an empirical study

FAHLMAN S. E.
Proceedings of the 1988 Connectionist Models Summer School, 3851, 1989
Cited by (1)

12
 <no title>

HERTZ J.
INTRODUCTION TO THE THEORY OF NEURAL COMPUTATION, 1991
Cited by (104)

13
 Improving the learning rate of backpropagation with the gradient reuse algorithm

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

14
 <no title>

JELINEK F.
Probabilistic Information Theory : Discrete and memoryless models, 1968
Cited by (2)

15
 Optimization techniques applied to neural networks: line search implementation for back propagation

JONES K. L.
Proceedings of the International Joint Conference on Neural Networks 3, 933939, 1990
Cited by (1)

16
 Efficient parallel learning algorithms for neural networks

KRAMER A. H.
Advances in neural information processing systems 1, 4048, 1988
Cited by (1)

17
 Learning to tell two spirals apart

LANG K. J.
Proceedings of the 1988 Connectionist Models Summer school, 5259, 1989
Cited by (1)

18
 Empirical comparison of flatspot elimination techniques in backpropagation networks

PAREKH R.
SPIE Proceedings (3rd Workshop on Neural Networks) 5560, 1721, 1993
Cited by (1)

19
 Backpropagation algorithm with controlled oscillation of weights

PIREZ Y. M.
Proceedings of the IEEE International Conference on Neural Networks 1, 2126, 1993
Cited by (1)

20
 <no title>

PITTNER S.
Basics for conjugate gradient minimum search, 1996
Cited by (1)

21
 <no title>

POLAK E.
Computational Methods in Optimization: A Unified Approach, 1971
Cited by (3)

22
 Note sur la convergence de methodes de directions conjuguees

POLAK E.
Revue Francaise d'Informatique et de Recherche Operationnelle 16, 3543, 1969
Cited by (1)

23
 <no title>

PRESS W. H.
Numerical recipes in C: the art of scientific computing 2, 1992
Cited by (2)

24
 Nearoptimal dynamic learning rate for training backpropagation neural networks

ROY S.
Science of Artificial Neural Networks II, 277283, 1993
Cited by (1)

25
 <no title>

RUMELHART D. E.
Parallel distributed processing: explorations in the microstructure of cognition: foundations 1, 1986
Cited by (1)

26
 <no title>

RYAN T. P.
Modern regression methods., 1997
Cited by (3)

27
 Parallel networks that learn to pronounce english text

SEJNOWSKI T. J.
Complex Systems 1(1), 145168, 1987
Cited by (1)

28
 <no title>

SILVA F. M.
Acceleration techniques for the backpropagation algorithm, 110119, 1990
Cited by (1)

29
 Escape from the slowdown area on training of backpropagation algorithm by using a jumping method

YAMADA K.
Systems and Computers in Japan 28(4), 4857, 1997
Cited by (1)

30
 A new acceleration technique for the backpropagation algorithm

YU X.
Proceedings of the IEEE International Conference on Neural Networks 3, 11571161, 1993
Cited by (1)

31
 Firstand secondorder methods for learning between steepest and descent newton's method

BATTITI R.
Neural Computation 4(2), 141166, 1992
DOI Cited by (22)

32
 Conjugate gradient algorithm for efficient training of artificial neural networks

CHARALAMBOUS C.
IEEE Proc. G. 139, 301309, 1992
Cited by (6)

33
 Approximation capability in C(R^^^n) by multilayer feedforward networks and related problems

CHEN T.
IEEE Transactions on Neural Networks 6(1), 2530, 1995
Cited by (3)

34
 Projectionbased methods for stepsize adaptation and their application to the training of feedforward artificial neural networks

CODRINGTON C. W.
Proceedings of the IEEE International Conference on Neural Networks 1, 7277, 1994
Cited by (1)

35
 Ship WakeDetection Procedure Using Conjugate Gradient Trained Artificial Neural Networks

FITCH J. P.
IEEE Trans. on Geoscience and Remote Sensing 29(5), 718726, 1991
DOI Cited by (3)

36
 Global convergence properties of conjugate gradient methods for optimization

GILBERT J. C.
SIAM Journal on Optimization 2(1), 2142, 1992
DOI Cited by (1)

37
 Increased Rates of Convergence Through Learning Rate Adaptation

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

38
 Acceleration by prediction for error backpropagation algorithm of neural network

KANDA A.
Systems and Computers in Japan 25(1), 7887, 1994
DOI Cited by (1)

39
 Improvement of the backpropagation algorithm for training neural networks

LEONARD J.
Computers and Chemical Engineering 14(3), 337341, 1990
Cited by (2)

40
 Approximation by superposition of sigmoidal and radial basis functions

MHASKAR H. N.
Advances in Applied Mathematics 13, 350373, 1992
DOI Cited by (11)

41
 Two adaptive stepsize rules for gradient descent and their application to the training of feedforward artificial neural networks

MOHANDES M.
Proceedings of the IEEE International Conference on Neural Networks 1, 555560, 1994
Cited by (1)

42
 A first order adaptive learning rate algorithm for back propagation networks

NACHTSHEIM P. R.
Proceedings of the IEEE International Conference on Neural Networks 1, 257262, 1994
Cited by (1)

43
 Speedingup backpropagationa comparison of orthogonal techniques

PFISTER M.
Proceedings of the International Joint Conference on Neural Networks 1, 517523, 1993
Cited by (1)

44
 Restart procedures for the conjugategradient methods

POWELL M. J. D.
Math. Program. 12, 241254, 1977
Cited by (7)

45
 Modified quasiNewton methods for training neural networks

ROBITAILLE B.
Computers and Chemical Engineering 20(9), 11331140, 1996
Cited by (1)

46
 Effects of learning parameters and data presentation on the performance of backpropagation networks for milk yield prediction

SALEHI F.
Transactions of the ASAE 41(1), 253259, 1998
Cited by (1)

47
 Accelerating backpropagation through dynamic selfadaptation

SALOMON Ralf
Neural Networks 9(4), 589601, 1996
DOI Cited by (2)

48
 Asymptotic convergence of backpropagation

TESAURO G.
Neural Computation 1(3), 382391, 1989
DOI Cited by (1)

49
 Training a neural network with conjugate gradient methods

TOWSEY M.
Proceedings of the IEEE International Conference on Neural Networks 1, 373378, 1995
Cited by (1)

50
 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: 1

1
 Stability analysis of a threeterm backpropagation algorithm

ZWEIRI Yahya H. , SENEVIRATNE Lakmal D. , ALTHOEFER Kaspar
Neural networks : the official journal of the International Neural Network Society 18(10), 13411347, 20051201
References (19)