Abstract
Feed forward back-propagation artificial neural networks (ANNs) have been used to predict outcomes in a variety of biomedical settings [1],[2]. Their advantages and disadvantages compared with standard statistical methods (SSMs) relate to different appraisals of three major problems that are common to all methods for estimation: (1) agreement, (2) stability and (3) transparency. In this chapter we consider these problems and propose a method which addresses some of them using procedures called genetic algorithms. Our arguments are illustrated by comparing the performance of the various prediction methods in predicting the occurrence of depression after mania [3].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baxt, W. Application of neural networks to clinical medicine. Lancet, 346:1135–38, 1995.
Cross, S., Harrison, R., and Kennedy, R. Introduction to neural networks. Lancet, 346:1075–79, 1995.
Lucas, C., Rigby, J., and Lucas, S. The occurence of depression following mania: A method of predicting vulnerable cases. Br.J.Psych, 154:705–08, 1989.
White, H. Learning in artificial neural networks: A statistical approach. Neural Comp., 1:425–64, 1989.
Cybenko, G. Approximation by superpositions of a sigmoidal function. Math Control Sig Sys, 2:303–314, 1989.
Hornik, K., Stinchcombe, M., and White, H. Multilayer feedforward networks are universal approximators. Neural Networks, 2(5):359–366, 1989.
Minsky, M. and Papert, S. Perceptrons. Cambridge, Mass, CA.: MIT Press, 1989.
Wyatt, J. Nervous about artificial neural networks? Lancet, 346:1175–77, 1995.
Press, W., Teukolsky, S., and W. Vetterling, Numerical recipes in FORTRAN. The art of scientific computing. 2 ed. Cambridge University Press: Cambridge, UK, 1994.
Jefferson, M., et al. Comparison of a genetic algorithm neural network (GANN) with logistic regression for predicting outcome after surgery for non-small cell lung cancer (NSCLC). Cancer, 79:1338–42, 1997.
Jefferson, M., et al. Prediction of Haemorrhagic Blood Loss with a Genetic Algorithm Neural Network (GANN). J Appl. Physiol, 84(1):357–61, 1998.
Goldberg, D. Genetic Algorithms in Search, Optimization and Machine Learning. 1st ed. Reading, Mass., USA: Addison-Wesley, 1989.
Yao, X. A review of evolutionary artificial neural networks. Intelligent Sys, 8(4):539–67, 1993.
Branke, J. Evolutionary algorithms for neural network design and training. Karlsruhe University: Karlsruhe, Germany, 1995.
Balakrishnan, K., and Vasant, H. Evolutionary design of neural architectures: A preliminary taxonomy and guide to Literature. Iowa State University: Ames, Iowa, USA, 1995.
Narayanan, M., and Lucas, S. A genetic algorithm to improve a neural network to predict a patient’s response to warfarin. Methods Inform Med, 32:55–58, 1993.
Dybowski, R. et al. Prediction of outcome in critically ill patients using artificial neural network synthesized by genetic algorithm. Lancet, 347:114–650, 1996.
Rummelhart, D., Hinton, G., and Williams, R. Learning internal representations by error propagation., in Parallel distributed processing: explorations in the microstructure of cognition., D. Rummelhart and D. McClelland, Editors. MIT Press: Cambrige, Mass, USA. 1986.
Morgan, H. The incidence of depressive symptoms during recovery from hypomania. Brit J Psych, 120:537–39, 1972.
Hart, A., and Wyatt, J. Evaluating black boxes as medical decision-aids: Issues arising from a study of neural networks. Med Inf (lond).,15:229–36, 1990.
Amari, S. Learning and statistical inference, in Handbook of Brain Theory and Neural Networks, M. Arib, Editor. MIT Press: Cambridge, Mass, USA. 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag London
About this chapter
Cite this chapter
Jefferson, M.F., Pendleton, N., Lucas, S.B. (2000). Genetic Evolution of Neural Network Architectures. In: Lisboa, P.J.G., Ifeachor, E.C., Szczepaniak, P.S. (eds) Artificial Neural Networks in Biomedicine. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0487-2_4
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0487-2_4
Publisher Name: Springer, London
Print ISBN: 978-1-85233-005-7
Online ISBN: 978-1-4471-0487-2
eBook Packages: Springer Book Archive