Efficacy of Modified Backpropagation and Optimisation Methods on a Realworld Medical Problem

 ALPSAN Dogan
 Department of Biophysics, United Arab Emirates University

 TOWSEY Michael
 Department of Biophysics, United Arab Emirates University

 OZDAMAR Ozcan
 Department of Biomedical Engineering, University of Miami

 TSOI Ah Chung
 Department of Electrical Engineering, University of Queensland

 GHISTA Dhanjoo N.
 Department of Biophysics, United Arab Emirates University
Search this Article
Author(s)

 ALPSAN Dogan
 Department of Biophysics, United Arab Emirates University

 TOWSEY Michael
 Department of Biophysics, United Arab Emirates University

 OZDAMAR Ozcan
 Department of Biomedical Engineering, University of Miami

 TSOI Ah Chung
 Department of Electrical Engineering, University of Queensland

 GHISTA Dhanjoo N.
 Department of Biophysics, United Arab Emirates University
Journal

 Neural Networks

Neural Networks 8(6), 945962, 19950801
References: 50

1
 Auditory brainstem evoked potential classification for threshold detection by neural networks I. Network design, similarities between humanexpert and network classification, feasibility

ALPSAN D.
Automedica 15, 6782, 1992
Cited by (1)

2
 Auditory brainstem evoked potential classification for threshold detection by neural networks. II. Effects of input coding, training set size and composition and network size on performance

ALPSAN D.
Automedica 15, 8393, 1992
Cited by (1)

3
 Onedimensional search strategies for conjugate gradient training of backpropagation neural networks

AYLWARD S.
Proceedings of the Artificial Neural Networks in Engineering (ANNIE '92) Conference 2, 197202, 1992
Cited by (1)

4
 A deviation of conjugate gradients.

BEALE E. M. L.
Numerical Methods for Nonlinear Optimization, 3943, 1972
Cited by (1)

5
 Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters.

BRIDLE J. S.
Advances in Neural Information Processing Systems 2, 211217, 1990
Cited by (1)

6
 A comparison study of the gradient descent and the conjugate gradient backpropagation neural networks

CHEN C. H.
World Congress on Neural Networks III, 401406, 1993
Cited by (1)

7
 Stepsize variation methods for accelerating the back propagation algorithm

CHEN J. R.
Proceedings of the International Joint Conference on Neural Networks 1, 601604, 1990
Cited by (1)

8
 Fastlearning variations on back propagation: an empirical study.

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

9
 <no title>

GILL P. E.
Practical Optimization, 1981
Cited by (31)

10
 Equivalence proofs for multilayer perceptron classifiers and the Bayesian discriminant function.

HAMPSHIRE II J. B.
Connectionist Models. Proceedings of the 1990 Connectionist Models Summer School, 159172, 1990
Cited by (1)

11
 Numerical analysis and adaptation method for learning rate of back propagation

HIGASHINO J.
Proceedings of the International Joint Conference on Neural Networks 1, 627630, 1990
Cited by (1)

12
 Improvement on function approximation capability of backpropagation neural networks

LEE J.
Proceedings of the International Joint Conference on Neural Networks II, 13671372, 1991
Cited by (1)

13
 Complete solution of the local minima in the XOR problem

LISBOA P. J. G.
Network 2, 119124, 1991
Cited by (6)

14
 Acceleration of backpropagation through learning rate and momentum adaptation

MINAI A. A.
Proceedings of the International Joint Conference on Neural Networks I, 676679, 1990
Cited by (1)

15
 <no title>

PLAUT D. C.
Experiments on learning by back propagation (CMUCS86126), 1988
Cited by (1)

16
 <no title>

PRESS W. H.
Numerical recipes in Pascal : the art of scientific computing., 1989
Cited by (5)

17
 <no title>

RAO S. S.
Optimization; Theory and Applications, 1978
Cited by (2)

18
 Backpropagation improvements based heuristic arguments

SAMAD T.
Proceedings of the International Joint Conference on Neural Networks I, 565568, 1990
Cited by (1)

19
 Speeding up back propagation by gradient correlation

SCHREIBMAN D. V.
Proceedings of the International Joint Conference on Neural Networks I, 723726, 1990
Cited by (1)

20
 Accelerated learning in layered neural networks

SOLLA S. A.
Complex Systems 2, 625640, 1988
Cited by (4)

21
 Scaling relationships in backpropagation learning.

TESAURO G.
Complex Systems 2, 3944, 1988
Cited by (3)

22
 Accelerating the convergence of the backpropagation method

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

23
 Back propagation, weightelimination and time series prediction

WEIGEND A. S.
Connectionist Models. Proceedings of the 1990 Connectionist Models Summer School, 105116, 1991
Cited by (1)

24
 Determining hearing threshold from brain stem evoked potentialsoptimising a neural network to improve classification performance

ALPSAN D.
IEEE Engineering in Medicine and Biology Magazine 13, 465471, 1994
DOI Cited by (1)

25
 Optimization for training neural nets

BARNARD E.
IEEE Trans. Neural Networks 3(2), 232240, 1992
Cited by (5)

26
 A comparative study of optimisation techniques for backpropagation

BARNARD E.
Neurocomputing 6, 1930, 1994
Cited by (1)

27
 Firstand secondorder methods for learning between steepest and descent newton's method

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

28
 Learning with first second and no derivatives: a case study in high energy physics.

BATTITI R.
Neurocomputing 6, 181206, 1994
Cited by (2)

29
 'Plain backpropagation' and advanced optimisation algorithms: a comparative study

DE GROOT C.
Neurocomputing 6, 153161, 1994
Cited by (1)

30
 Speech Recognition with Back Propagation

FRANZINI M. A.
9th Annual Conf. IEEE Engn. Medic. Biol. Soc., 1987. 11, 1987
Cited by (3)

31
 A novel objective function for improved phoneme recognition using time delay neural networks

HAMPSHIRE II J. B.
IEEE Trans. Neural Netw. 1(2), 216228, 1990
Cited by (6)

32
 Convergence of back propagation in neural networks using a loglikelihood cost function

HOLT M. J.
Electron. Lett. 26, 19641965, 1990
Cited by (3)

33
 Multilayer feedforward neural networks are universal approximators

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

34
 Analysis of neural networks with redundancy

IZUI Y.
Neural Computation 2, 226238, 1990
DOI Cited by (2)

35
 Increased Rates of Convergence Through Learning Rate Adaptation

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

36
 Backpropagation applied to handwritten zip code recognition

LECUN Y.
Neural Computation 1, 541551, 1989
DOI Cited by (33)

37
 Backpropagation based on the logarithmic error function and elimination of local minima

MATSUOKA K.
Proceedings of the International Joint Conference on Neural Networks II, 11171122, 1991
Cited by (1)

38
 A scaled conjugate gradient algorithm for fast supervised learning

MOLLER M. F.
Neural Networks 6(4), 525533, 1993
Cited by (18)

39
 Neural networks and nonlinear adaptive filtering: unifying concepts and new algorithms.

NERRAND O.
Neural Computation 5, 165199, 1993
DOI Cited by (5)

40
 Restart procedures for the conjugategradient methods

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

41
 Neural network classifiers estimate Bayesian a posteriori probabilities

RICHARD
Neural Computation 3, 461483, 1991
DOI Cited by (22)

42
 Learning representations by backpropagation errors

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

43
 Conjugate gradient methods with inexact searches

SHANO D. F.
Mathematics of Operations Research 3(3), 244256, 1978
Cited by (6)

44
 Back propagation learning with trinary quantization of weight update

SHOEMAKER P. A.
Neurla Networks 4, 231241, 1991
Cited by (4)

45
 <no title>

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

46
 SuperSAB : Fast adaptive backpropagation with good scaling properties

TOLLENAERE T.
Neural Netw. 3, 561573, 1990
Cited by (13)

47
 Minimization Methods for Training Feedforward Neural Network

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

48
 Improving the convergence of the backpropagation algorithm

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

49
 Auditory brainstem response classification using modular neural networks

WEN H.
Proceedings of the IEEE/Thirteenth Annual Conference of the Engineering in Medicine and Biology Society 13(4), 18791880, 1991
Cited by (1)

50
 Learning in artificial neural networks : A statistical perspective

WHITE H.
Neural Computation 1, 425464, 1989
DOI Cited by (24)
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
 Introduction of Orthonormal Transform into Neural Filter for Accelerating Convergence Speed

NAKANISHI Isao , ITOH Yoshio , FUKUI Yutaka
IEICE transactions on fundamentals of electronics, communications and computer sciences 83(2), 367370, 20000225
References (12)